© 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. 10-GEMMASCOPE-RES-131K
    7. 12092
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    string values in JSON or structured configuration files, particularly those specifying types, scales, or identifiers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     to
    -1.80
     our
    -1.65
     namely
    -1.63
     who
    -1.59
     said
    -1.44
     eficiente
    -1.34
     不能
    -1.33
     «
    -1.32
     the
    -1.30
     той
    -1.29
    POSITIVE LOGITS
     with
    1.78
     if
    1.63
    あっという間に
    1.55
     във
    1.47
    quelize
    1.42
    voorbeeld
    1.42
    {~
    1.38
    tronlink
    1.37
    既に
    1.36
     katika
    1.34
    Activations Density 0.034%

    No Known Activations