© 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. 65826
    Prev
    Next
    INDEX
    Explanations

    workout titles and descriptions

    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
     Forster
    -0.78
    Dialogue
    -0.76
    Reel
    -0.75
     Scalar
    -0.74
     Reel
    -0.74
    tecla
    -0.73
    Kanal
    -0.73
     WINTER
    -0.73
     پشت
    -0.73
     Tâm
    -0.72
    POSITIVE LOGITS
     PAX
    0.92
     Pax
    0.89
     pax
    0.86
     childcare
    0.86
    Pax
    0.83
    ǽ
    0.81
    ksanakan
    0.79
     headlamp
    0.78
     Hash
    0.77
    AO
    0.77
    Activations Density 0.003%

    No Known Activations