© 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. 25165
    Prev
    Next
    INDEX
    Explanations

    vintage items and styles

    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
    Negative Logits
    犼
    -2.61
    肏
    -2.36
    拊
    -2.31
    慫
    -2.16
    馓
    -2.11
    塍
    -2.11
    鞫
    -2.11
     ビキニ
    -2.06
    簠
    -2.05
    푆
    -2.03
    POSITIVE LOGITS
    While
    2.78
    Despite
    2.75
    Having
    2.64
    i
    2.58
    It
    2.53
    If
    2.53
    However
    2.45
    This
    2.42
    Although
    2.42
    Another
    2.36
    Activations Density 0.008%

    No Known Activations