© 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. 34-GEMMASCOPE-RES-131K
    7. 110545
    Prev
    Next
    INDEX
    Explanations

    MotoGP, Russian Anti-Doping Agency, Global Title

    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_34/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
     from
    -0.90
     nestled
    -0.89
     took
    -0.88
     on
    -0.86
     unrelenting
    -0.85
    vum
    -0.79
    !!!!!
    -0.78
     in
    -0.78
     unparalleled
    -0.78
     didnt
    -0.77
    POSITIVE LOGITS
     splendid
    0.98
    خوب
    0.93
    퐸
    0.91
     ñ
    0.89
     geboten
    0.89
    ,​
    0.87
     koniec
    0.86
    ourced
    0.84
     ozdob
    0.84
    Perman
    0.84
    Activations Density 0.000%

    No Known Activations