© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128454
    Prev
    Next
    INDEX
    Explanations

    theatre and auditorium

    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
    椟
    -2.06
     pokoj
    -2.02
    CurtirCurtir
    -1.98
     projekty
    -1.97
    筴
    -1.86
     Utiliza
    -1.84
    訢
    -1.81
    眛
    -1.80
    を観
    -1.80
     péro
    -1.79
    POSITIVE LOGITS
    <em>
    2.02
     or
    1.91
    "
    1.89
     "
    1.84
    </code>
    1.81
    [
    1.80
    :
    1.80
     t
    1.79
     S
    1.77
    (
    1.71
    Activations Density 0.008%

    No Known Activations