© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35169
    Prev
    Next
    INDEX
    Explanations

    software license boilerplate

    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
     ADVICE
    -1.15
    actéristi
    -1.15
     mépris
    -1.09
     RECIPES
    -1.07
     recevoir
    -1.07
     catég
    -1.07
     bisous
    -1.06
     PUSH
    -1.06
     EXPLANATION
    -1.05
    撂
    -1.05
    POSITIVE LOGITS
     and
    1.87
     on
    1.44
     should
    1.34
     like
    1.29
     as
    1.29
     with
    1.27
     first
    1.26
     by
    1.23
     has
    1.23
     three
    1.19
    Activations Density 0.002%

    No Known Activations