© 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. 22-GEMMASCOPE-RES-131K
    7. 16157
    Prev
    Next
    INDEX
    Explanations

    code delimiters and variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    OfWork
    -0.98
     Keuangan
    -0.97
     EconPapers
    -0.96
     with
    -0.94
    epy
    -0.93
     davidson
    -0.90
     during
    -0.89
    více
    -0.88
     berkaitan
    -0.86
    ckeye
    -0.86
    POSITIVE LOGITS
    Their
    0.90
    ということを
    0.84
    他们
    0.84
    ということ
    0.81
     sonrisa
    0.75
    だけです
    0.75
     cuja
    0.75
    gründet
    0.73
     hech
    0.72
     вопло
    0.72
    Activations Density 0.046%

    No Known Activations