© 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. 107922
    Prev
    Next
    INDEX
    Explanations

    layer adjustment, duplicate, blending

    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
    jTable
    -0.77
     selfie
    -0.74
    équilibre
    -0.72
    LoggerFactory
    -0.71
     bidang
    -0.71
    writeFileSync
    -0.70
     cristales
    -0.69
    帼
    -0.68
    DrawLine
    -0.68
    textTheme
    -0.68
    POSITIVE LOGITS
     layer
    0.96
    プレイヤー
    0.88
     Adjustment
    0.86
     duplicated
    0.84
     blending
    0.83
    Locked
    0.82
     lowered
    0.81
    rogation
    0.81
    Layer
    0.80
     duplicate
    0.77
    Activations Density 0.015%

    No Known Activations