© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61119
    Prev
    Next
    INDEX
    Explanations

    code comments and tags

    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
     and
    -3.31
     in
    -2.81
     as
    -2.80
     at
    -2.59
     to
    -2.58
     with
    -2.23
     by
    -2.23
     or
    -2.19
     where
    -2.16
     before
    -2.11
    POSITIVE LOGITS
     eſſ
    2.53
     craindre
    2.45
     rigue
    2.44
     incrí
    2.42
     mauva
    2.39
     diriger
    2.30
    鮡
    2.30
     élas
    2.27
     vatten
    2.27
     estadounid
    2.27
    Activations Density 0.000%

    No Known Activations