© 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. 972
    Prev
    Next
    INDEX
    Explanations

    Python imports and libraries

    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
    っけ
    -0.93
     paroles
    -0.88
    古墳
    -0.85
     GUR
    -0.81
    roles
    -0.81
     PLAYERS
    -0.80
    matrix
    -0.79
    MathML
    -0.79
    薨
    -0.78
     Ems
    -0.78
    POSITIVE LOGITS
     município
    1.02
     torch
    0.98
     audition
    0.94
    蒸
    0.91
     Cllr
    0.91
     dataset
    0.90
     FLAGS
    0.88
     Audiodateien
    0.88
    torch
    0.88
    absl
    0.87
    Activations Density 0.015%

    No Known Activations