© 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. 102076
    Prev
    Next
    INDEX
    Explanations

    structured data fields and documentation

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

    documentation formatting with parameter descriptions, particularly colons followed by type specifications or metadata fields.

    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
    red
    -1.54
    他们
    -1.49
     them
    -1.47
     recens
    -1.45
     moſt
    -1.41
    v
    -1.40
    ted
    -1.40
    TargetException
    -1.38
    public
    -1.34
    ang
    -1.33
    POSITIVE LOGITS
     that
    1.70
     when
    1.54
     zarówno
    1.47
     because
    1.45
    because
    1.39
    ēc
    1.38
     how
    1.38
     unless
    1.38
     Lainnya
    1.35
     Uang
    1.35
    Activations Density 0.020%

    No Known Activations