© 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. 34-GEMMASCOPE-RES-131K
    7. 31491
    Prev
    Next
    INDEX
    Explanations

    code segments with punctuation

    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_34/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
    などは
    -0.73
     zoos
    -0.73
     Tense
    -0.73
     lenses
    -0.72
    ldb
    -0.71
    Crust
    -0.70
    ha
    -0.69
    などを
    -0.69
     chaise
    -0.68
     Lenses
    -0.68
    POSITIVE LOGITS
     Però
    0.94
    Contexts
    0.87
     ctx
    0.86
     svoj
    0.84
    children
    0.83
     recog
    0.82
    ⏱
    0.82
    haltet
    0.81
     Drž
    0.81
    localctx
    0.80
    Activations Density 0.001%

    No Known Activations