© 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. 118826
    Prev
    Next
    INDEX
    Explanations

    Lord Vishnu incarnations

    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
    ℃
    -0.93
    ESTIC
    -0.81
     marketed
    -0.80
     diagnosed
    -0.80
    姊
    -0.78
    ƈ
    -0.78
     Mitarbeitern
    -0.78
     aromatic
    -0.77
     Schülern
    -0.76
    melten
    -0.76
    POSITIVE LOGITS
     Vishnu
    0.90
    维持
    0.77
    Création
    0.74
     avatars
    0.73
     ICS
    0.72
    dvi
    0.71
    yti
    0.70
    creator
    0.70
     manu
    0.69
     Brahma
    0.69
    Activations Density 0.020%

    No Known Activations