© 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. 93205
    Prev
    Next
    INDEX
    Explanations

    enumerated items followed by 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
    Sushi
    -0.90
    sushi
    -0.87
    することも
    -0.78
     删除
    -0.77
     sushi
    -0.74
     הרב
    -0.72
     tasty
    -0.71
     cinese
    -0.71
     wtedy
    -0.71
     delicious
    -0.70
    POSITIVE LOGITS
     дописавши
    0.96
    餐
    0.95
    ТУ
    0.90
    EClass
    0.89
     graf
    0.89
     plating
    0.86
     wedges
    0.85
     earl
    0.85
    gao
    0.84
     Oculus
    0.82
    Activations Density 0.011%

    No Known Activations