© 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. 22-GEMMASCOPE-RES-131K
    7. 15360
    Prev
    Next
    INDEX
    Explanations

    CWE and definitions

    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
     at
    -1.35
     so
    -1.17
     three
    -1.12
     from
    -1.12
     する
    -1.11
     first
    -1.08
     significant
    -1.07
     all
    -1.06
    cvtColor
    -1.04
     system
    -1.02
    POSITIVE LOGITS
     saludables
    1.28
     封面
    1.21
     unn
    1.20
    これも
    1.16
    每一次
    1.15
    最后由
    1.15
     fornecer
    1.14
    providing
    1.13
     dasselbe
    1.12
     melhorar
    1.11
    Activations Density 0.002%

    No Known Activations