© 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. 22-GEMMASCOPE-RES-131K
    7. 9636
    Prev
    Next
    INDEX
    Explanations

    function/component names

    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_22/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
     on
    -2.05
     in
    -1.97
     with
    -1.78
    </h1>
    -1.69
     an
    -1.52
     at
    -1.44
     (
    -1.38
     makes
    -1.36
     from
    -1.36
     or
    -1.36
    POSITIVE LOGITS
    <bos>
    1.74
     DURING
    1.56
     enigmatic
    1.51
     hauptsächlich
    1.51
     různých
    1.48
     jenes
    1.41
     estarán
    1.40
     afore
    1.39
     marvelous
    1.36
     haupts
    1.36
    Activations Density 0.053%

    No Known Activations