© 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. 12299
    Prev
    Next
    INDEX
    Explanations

    % followed by digits or alphanumeric

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

    whitespace or tab characters, particularly at the beginning of lines or in structured code/data formatting.

    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
     it
    -2.13
     then
    -1.63
     their
    -1.62
    :
    -1.45
     —
    -1.45
     when
    -1.41
     zrobić
    -1.40
     who
    -1.38
     what
    -1.37
     how
    -1.37
    POSITIVE LOGITS
    都在
    1.46
     OGSÅ
    1.46
     ECONOMY
    1.44
    豋
    1.44
    ̴
    1.42
     "");
    1.38
    emptions
    1.35
    extAlignment
    1.34
     sebagainya
    1.34
     APPROVAL
    1.33
    Activations Density 0.002%

    No Known Activations