© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16381
    Prev
    Next
    INDEX
    Explanations

    time, watching, thinking

    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_22/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
    サキ
    -0.87
    ↵↵↵
    -0.86
     чого
    -0.84
     podamos
    -0.81
    lingua
    -0.78
    zki
    -0.78
     nunca
    -0.77
    INTAGE
    -0.77
    Netto
    -0.77
    ↵↵↵↵
    -0.74
    POSITIVE LOGITS
     sitting
    1.03
    telah
    1.00
    fillment
    0.97
     watching
    0.95
     thinking
    0.91
    箓
    0.91
     μαύ
    0.90
    ７
    0.90
    ⲣ
    0.89
     moments
    0.89
    Activations Density 0.034%

    No Known Activations