© 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. 10-GEMMASCOPE-RES-131K
    7. 60066
    Prev
    Next
    INDEX
    Explanations

    council members and proceedings

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

    The neuron activates on mentions of “council,” i.e. references to local governing bodies.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    潆
    -3.25
    
    -3.19
    翼翼
    -3.11
    Ꮞ
    -2.95
    拶
    -2.88
    艄
    -2.80
    旯
    -2.72
    ୩
    -2.61
     unſ
    -2.55
     dê
    -2.53
    POSITIVE LOGITS
    I
    3.50
    man
    3.16
    "
    2.94
    to
    2.92
    is
    2.88
    );
    2.78
    (
    2.70
    <td>
    2.69
    are
    2.67
    It
    2.64
    Activations Density 0.005%

    No Known Activations