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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 724
    Prev
    Next
    INDEX
    Explanations

    endings and blockages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    葙
    -1.82
     äta
    -1.80
    椟
    -1.79
    鈈
    -1.72
     Settembre
    -1.71
    ڧ
    -1.70
    ＾＾；
    -1.68
     parteci
    -1.63
    贇
    -1.63
     cuando
    -1.62
    POSITIVE LOGITS
     '
    2.88
    ="
    2.08
    "
    2.06
    to
    1.85
    )
    1.70
    '
    1.70
    ..."
    1.69
    ll
    1.66
    ...."
    1.66
    {~
    1.59
    Activations Density 0.004%

    No Known Activations