© 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. 110555
    Prev
    Next
    INDEX
    Explanations

    amount of time spent

    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
    thing
    -0.86
    ȁ
    -0.85
    렴
    -0.84
    блемы
    -0.83
    ulated
    -0.81
    collana
    -0.81
    spending
    -0.79
    hasta
    -0.77
     ditem
    -0.77
    -}
    -0.77
    POSITIVE LOGITS
     time
    2.98
     времени
    1.73
    time
    1.45
     czasu
    1.37
     aikaa
    1.30
     energy
    1.24
     times
    1.19
     समय
    1.18
     of
    1.17
     време
    1.16
    Activations Density 0.016%

    No Known Activations