© 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. 34-GEMMASCOPE-RES-131K
    7. 49457
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
    袛
    -0.84
    ホルダー
    -0.81
     volle
    -0.81
    เริ่ม
    -0.80
    まずは
    -0.80
     semua
    -0.80
    źdz
    -0.80
    obviously
    -0.79
     kwanza
    -0.79
     obvio
    -0.78
    POSITIVE LOGITS
     suffix
    1.05
    (:,:,
    1.02
    suffix
    1.02
    ='/
    0.95
    ":
    0.94
     ":
    0.93
     space
    0.91
    :'/
    0.89
    ':
    0.88
    Futures
    0.88
    Activations Density 0.025%

    No Known Activations