© 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. 25264
    Prev
    Next
    INDEX
    Explanations

    learning about or how to

    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
    ↵
    -2.09
    鋱
    -2.08
    ｲ
    -1.95
    呖
    -1.81
     guapos
    -1.81
    เกง
    -1.77
     которой
    -1.69
     คือ
    -1.59
     diesen
    -1.58
    e
    -1.58
    POSITIVE LOGITS
     about
    2.67
     how
    2.22
    
    2.17
     from
    2.02
    :");
    1.98
     Tonnen
    1.96
     enough
    1.92
     to
    1.91
     花纹
    1.88
    ®:
    1.83
    Activations Density 0.017%

    No Known Activations