© 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. 119043
    Prev
    Next
    INDEX
    Explanations

    names and phrases

    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
    йся
    -0.95
    doGet
    -0.88
     juni
    -0.87
     coeur
    -0.85
    isy
    -0.85
    orios
    -0.84
    '`
    -0.84
    ilation
    -0.83
    iric
    -0.83
     Foxx
    -0.82
    POSITIVE LOGITS
    Conse
    0.86
     wünscht
    0.85
     aceste
    0.84
     brachte
    0.83
    特別な
    0.83
    rister
    0.79
    商店街
    0.79
     declaró
    0.79
     aiuta
    0.78
     suffering
    0.76
    Activations Density 0.000%

    No Known Activations