© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113411
    Prev
    Next
    INDEX
    Explanations

    programming keywords and constructs

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

    type annotations or declarations in programming code, particularly for classes, interfaces, and function parameters.

    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
    m
    -2.56
    y
    -1.95
    at
    -1.88
    f
    -1.88
    on
    -1.77
     abomination
    -1.76
    g
    -1.69
     інші
    -1.69
     було
    -1.63
    tahui
    -1.60
    POSITIVE LOGITS
     circunstan
    1.69
    艄
    1.65
    RICIA
    1.64
     usado
    1.64
    ‪.‬‬
    1.63
    ਗ਼
    1.61
     cualquier
    1.59
    罴
    1.59
     usamos
    1.58
     depender
    1.58
    Activations Density 0.014%

    No Known Activations