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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8660
    Prev
    Next
    INDEX
    Explanations

    links to http addresses

    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
    renos
    -0.73
    unbind
    -0.71
     NAM
    -0.69
     Tiwari
    -0.68
     iodine
    -0.68
     במ
    -0.68
    steps
    -0.67
    rago
    -0.67
    ील
    -0.65
    sche
    -0.64
    POSITIVE LOGITS
    ArrayType
    0.67
     EDUCATION
    0.67
    샐
    0.66
    シャレ
    0.66
    Ish
    0.65
    werking
    0.64
     roulette
    0.63
    protective
    0.63
    Genetics
    0.62
    carhartt
    0.61
    Activations Density 0.080%

    No Known Activations