© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111819
    Prev
    Next
    INDEX
    Explanations

    following colon `:`

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

    punctuation marks that denote a type signature or return type in code, particularly the colon followed by closing parenthesis in function declarations.

    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
    f
    -1.84
     enticing
    -1.75
    da
    -1.69
     in
    -1.66
    si
    -1.66
     dazzling
    -1.66
     Giving
    -1.63
    1
    -1.60
     to
    -1.60
    ol
    -1.59
    POSITIVE LOGITS
     the
    1.97
     également
    1.91
     также
    1.87
     complètement
    1.86
    
    1.80
     oggi
    1.80
     our
    1.79
    灩
    1.78
     seyn
    1.73
     começ
    1.72
    Activations Density 0.000%

    No Known Activations