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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8338
    Prev
    Next
    INDEX
    Explanations

    Cochrane Register

    np_acts-logits-general · gemini-2.5-flash-lite

    programming and technical documentation elements, particularly in code files, academic papers, and database references.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     besz
    -0.70
     delgado
    -0.68
     benötigen
    -0.67
    правля
    -0.67
    jø
    -0.67
    لمانيا
    -0.67
    ávají
    -0.66
    ⋊
    -0.65
     Сте
    -0.65
     lagi
    -0.65
    POSITIVE LOGITS
     takers
    0.79
     abarca
    0.75
    हरू
    0.65
    OUR
    0.65
    ulur
    0.63
     Sev
    0.63
     идет
    0.62
     outcome
    0.62
    LABOR
    0.62
     valves
    0.61
    Activations Density 0.095%

    No Known Activations