© 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. 16699
    Prev
    Next
    INDEX
    Explanations

    object/class names

    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
     in
    -1.59
    textAlignment
    -1.26
    子は
    -1.16
     by
    -1.14
    ～！
    -1.12
    setAccessible
    -1.11
    crops
    -1.10
     Ży
    -1.09
    🦠
    -1.08
     catalana
    -1.07
    POSITIVE LOGITS
    必要がある
    1.38
    為に
    1.37
    の良い
    1.23
    色んな
    1.21
    譏
    1.20
    になってしまう
    1.17
    必要があります
    1.16
    Inhalts
    1.16
    色々と
    1.13
    色々な
    1.11
    Activations Density 0.018%

    No Known Activations