© 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. 22-GEMMASCOPE-RES-131K
    7. 13657
    Prev
    Next
    INDEX
    Explanations

    of sentences or phrases

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

    The neuron strongly activates on numeric and quantitative expressions (e.g., digits, measurements, counts, and other number‐related tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     algum
    -0.88
     irgende
    -0.87
    zsef
    -0.84
     thorny
    -0.82
     variétés
    -0.82
     weißem
    -0.82
     vilken
    -0.81
     heridos
    -0.81
    ICHT
    -0.81
     oferec
    -0.81
    POSITIVE LOGITS
     instead
    1.40
     rather
    1.05
     auroit
    1.00
    Instead
    0.99
    место
    0.96
    remos
    0.96
    cách
    0.96
     plutôt
    0.94
    Rather
    0.94
    Todd
    0.91
    Activations Density 0.087%

    No Known Activations