© 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. 16039
    Prev
    Next
    INDEX
    Explanations

    code and 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
    Not in Any Lists

    No Comments

    Negative Logits
     who
    -1.25
     What
    -1.25
     there
    -1.15
     How
    -1.13
     how
    -1.12
     would
    -1.10
     r
    -1.09
     h
    -1.09
     like
    -1.09
     had
    -1.08
    POSITIVE LOGITS
    ascin
    1.24
    parece
    1.22
     Pard
    1.19
    UEFA
    1.18
     NEEDS
    1.17
     クリーム
    1.16
     {
    1.15
    Terug
    1.15
    uaikan
    1.14
     impuesto
    1.14
    Activations Density 0.001%

    No Known Activations