© 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. 12169
    Prev
    Next
    INDEX
    Explanations

    function call syntax

    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
     and
    -1.49
     after
    -1.41
     both
    -1.34
     as
    -1.31
     for
    -1.19
     two
    -1.16
     because
    -1.16
     when
    -1.14
     will
    -1.13
     in
    -1.12
    POSITIVE LOGITS
    ?,?,
    1.39
    ","","
    1.15
     Spéc
    1.13
     maniere
    1.11
     intit
    1.09
     scatt
    1.05
     Certo
    1.05
     Haye
    1.03
     prenn
    1.03
    ああ
    1.03
    Activations Density 0.010%

    No Known Activations