© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118975
    Prev
    Next
    INDEX
    Explanations

    starring Nicole, Lea Michele album

    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
     О
    -0.81
    о
    -0.80
     Clearly
    -0.76
    なら
    -0.75
    ッサ
    -0.73
    Ϝ
    -0.71
    ᶠ
    -0.68
    возмо
    -0.68
    SCC
    -0.68
    OLOGÍA
    -0.67
    POSITIVE LOGITS
     bedien
    0.91
     ‐
    0.83
     باشه
    0.82
    lenght
    0.81
    ząc
    0.79
     oer
    0.77
     growing
    0.77
     Downloaded
    0.77
    ましい
    0.77
    叆
    0.76
    Activations Density 0.907%

    No Known Activations