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. 7967
    Prev
    Next
    INDEX
    Explanations

    URL paths and code comments

    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
     Tacitus
    -0.74
    jazdu
    -0.72
     scound
    -0.71
     Tul
    -0.71
     Maur
    -0.70
     Scaffold
    -0.69
     Amal
    -0.69
    Controller
    -0.69
    Scaffold
    -0.69
     Estonia
    -0.69
    POSITIVE LOGITS
     late
    0.75
     cant
    0.73
    referral
    0.70
     μή
    0.66
     Beasley
    0.65
    romi
    0.64
     провин
    0.63
     Holloway
    0.63
    ða
    0.62
    海上
    0.62
    Activations Density 0.056%

    No Known Activations