© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67357
    Prev
    Next
    INDEX
    Explanations

    for the sake of

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Using
    -1.31
     даже
    -1.27
     inapropiados
    -1.18
     beschreiben
    -1.16
     directement
    -1.15
    𝟏
    -1.14
    就连
    -1.14
     involucrados
    -1.11
    なんだろう
    -1.10
     kdo
    -1.07
    POSITIVE LOGITS
    _
    1.17
    狁
    1.16
     sake
    1.16
     {
    1.15
    igkeit
    1.14
     desember
    1.13
     AMERICA
    1.13
    琑
    1.12
    ##
    1.09
    의
    1.09
    Activations Density 0.043%

    No Known Activations