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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102581
    Prev
    Next
    INDEX
    Explanations

    HTML canvas and color definitions

    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_34/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
     vé
    -0.79
    culable
    -0.73
     pakan
    -0.70
    //*/
    -0.69
    ophi
    -0.69
    ᵉ
    -0.68
    enseur
    -0.68
     Erlangen
    -0.68
     Viet
    -0.67
    dies
    -0.67
    POSITIVE LOGITS
    QMetaType
    0.92
    rekli
    0.82
     shrew
    0.80
    ouple
    0.79
    Tuple
    0.79
    ganta
    0.78
    kommer
    0.77
    OCUS
    0.77
    AYLOR
    0.77
     bistro
    0.76
    Activations Density 0.016%

    No Known Activations