© 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. 76388
    Prev
    Next
    INDEX
    Explanations

    start with

    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
    みます
    -0.95
     aidé
    -0.93
     kedi
    -0.92
     ブルゾン
    -0.91
     coû
    -0.91
     mView
    -0.90
     borra
    -0.90
     informou
    -0.89
     ekonomi
    -0.89
     a
    -0.89
    POSITIVE LOGITS
     by
    2.58
     with
    2.02
     from
    1.83
     at
    1.58
     off
    1.06
     out
    0.97
     stejně
    0.95
    sieu
    0.95
    很久
    0.92
     like
    0.88
    Activations Density 0.038%

    No Known Activations