Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8513
    Prev
    Next
    INDEX
    Explanations

    code comments and includes

    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
    ثير
    -0.74
    NL
    -0.68
    Then
    -0.68
    lp
    -0.66
    nl
    -0.64
    優雅
    -0.64
    lake
    -0.64
    ona
    -0.63
    atase
    -0.62
     records
    -0.61
    POSITIVE LOGITS
    מק
    0.77
    DED
    0.73
    сай
    0.72
    บู
    0.72
    ACF
    0.71
     Aditya
    0.71
    valves
    0.70
     papy
    0.70
    Tutti
    0.69
     SGS
    0.68
    Activations Density 0.104%

    No Known Activations