© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97819
    Prev
    Next
    INDEX
    Explanations

    sharpening blades and knives

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron tracks token position within a document, activating more strongly on tokens appearing later in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of mechanical tools and instruments, especially bladed or cutting implements and their edges/sharpening or maintenance contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    words related to tools, instruments, and their maintenance (sharpening, cleaning, or wearing).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trucking
    -0.91
     Pipes
    -0.89
    Inhoud
    -0.88
    Pipes
    -0.88
    inę
    -0.84
    Kenmerken
    -0.84
    kleidung
    -0.83
    drucks
    -0.83
    Jahre
    -0.82
     piping
    -0.82
    POSITIVE LOGITS
     sharpened
    2.70
     sharpening
    2.69
     blade
    2.64
     sharpen
    2.56
     blades
    2.56
     sharpness
    2.53
     sharp
    2.42
     sharper
    2.03
    刃
    1.98
    sharp
    1.98
    Activations Density 0.065%

    No Known Activations