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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 92907
    Prev
    Next
    INDEX
    Explanations

    python function calls or dunder methods

    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
    跸
    -1.15
    alisation
    -1.14
    蒌
    -1.11
    があるので
    -1.09
     choses
    -1.09
     peda
    -1.09
     GETS
    -1.07
    亰
    -1.07
     Received
    -1.06
     hydrauli
    -1.06
    POSITIVE LOGITS
     or
    1.37
     and
    1.13
     lavish
    1.04
     unusually
    1.04
     extraordinarily
    1.02
     или
    0.99
     unwavering
    0.98
     undeniably
    0.98
    怪我
    0.97
     impressive
    0.96
    Activations Density 0.003%

    No Known Activations