© 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. 23666
    Prev
    Next
    INDEX
    Explanations

    unrestricted access, unincorporated community

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

    The neuron strongly activates on numeric tokens (especially four‐digit years or document identifiers) in the text.

    oai_token-act-pair · o4-miniTriggered 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
     sínt
    -0.99
    żyć
    -0.98
     総合
    -0.97
     uncertain
    -0.93
     undeniable
    -0.92
     qualcuno
    -0.91
     nėra
    -0.90
    u
    -0.88
     entsprechenden
    -0.88
     isn
    -0.88
    POSITIVE LOGITS
    Revenir
    0.99
    เช
    0.95
    蟆
    0.92
     untill
    0.91
     وغير
    0.91
    figcaption
    0.91
    lenia
    0.90
     but
    0.90
    ^{*}\
    0.89
    蟹
    0.87
    Activations Density 0.054%

    No Known Activations