© 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. 10-GEMMASCOPE-RES-131K
    7. 58184
    Prev
    Next
    INDEX
    Explanations

    on the fly, dynamically

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     to
    -1.64
    𖥧
    -1.58
     will
    -1.45
    石垣
    -1.44
    捋
    -1.36
    providedIn
    -1.33
    ició
    -1.31
     ....
    -1.30
     .....
    -1.30
    鹸
    -1.30
    POSITIVE LOGITS
    y
    1.63
    神
    1.45
     WHILE
    1.42
    Thrown
    1.38
    pagnols
    1.37
    읖
    1.35
    ができ
    1.34
     xào
    1.32
    determine
    1.31
     também
    1.30
    Activations Density 0.030%

    No Known Activations