© 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. 112941
    Prev
    Next
    INDEX
    Explanations

    behavioral descriptors

    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
    řeba
    -1.84
     ignited
    -1.80
    鋱
    -1.77
     showcased
    -1.72
     земли
    -1.63
    側は
    -1.60
     complimented
    -1.59
    Đặc
    -1.58
     bicicleta
    -1.57
    ◆◇
    -1.57
    POSITIVE LOGITS
    on
    2.14
    -
    1.81
    behavior
    1.74
     Utiliza
    1.72
    ”，
    1.70
     Behavior
    1.68
    .
    1.68
    </td>
    1.68
    K
    1.65
    」
    1.60
    Activations Density 0.037%

    No Known Activations