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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11383
    Prev
    Next
    INDEX
    Explanations

    next to, from

    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
    strophy
    -1.23
    ariConfig
    -1.10
     môžete
    -1.09
     ">=
    -1.05
    zmán
    -1.05
    gments
    -1.03
    imanapun
    -1.03
     {?>
    -1.02
     أي
    -1.01
    matory
    -1.01
    POSITIVE LOGITS
     the
    2.00
     other
    1.56
     similarly
    1.16
     where
    1.06
     another
    1.05
    他の
    1.04
    其它
    1.03
    其他
    1.01
     The
    1.00
    関連記事
    0.98
    Activations Density 0.044%

    No Known Activations