© 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. 31494
    Prev
    Next
    INDEX
    Explanations

    names starting with K

    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
     oxidative
    -0.82
    telijke
    -0.81
     K
    -0.74
    張
    -0.74
    ằ
    -0.73
    deinit
    -0.73
     wanneer
    -0.73
     beginning
    -0.72
    K
    -0.71
    ₁)
    -0.70
    POSITIVE LOGITS
    関連リンク
    0.78
     spezif
    0.74
    upuesto
    0.73
    Milestone
    0.71
    뤄
    0.70
     олив
    0.70
    シップ
    0.69
    stata
    0.69
    ၃
    0.69
    Halt
    0.69
    Activations Density 0.045%

    No Known Activations