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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35121
    Prev
    Next
    INDEX
    Explanations

    potential or ability

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

    The neuron activates on occurrences of the word “capacity” (including hyphenated forms like “capacity‐building”).

    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
    妧
    -3.20
    馓
    -2.97
    鹚
    -2.88
    垰
    -2.84
    鲧
    -2.81
    
    -2.81
     eſſ
    -2.77
     kapture
    -2.77
    鸱
    -2.73
     工房
    -2.69
    POSITIVE LOGITS
     It
    3.28
    e
    3.08
    ?
    3.05
     *
    2.84
    s
    2.67
    In
    2.64
    {
    2.42
    </h4>
    2.41
    h
    2.41
     The
    2.38
    Activations Density 0.012%

    No Known Activations