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. 7936
    Prev
    Next
    INDEX
    Explanations

    software documentation or metadata

    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
    unga
    -0.71
     labdar
    -0.69
     nasty
    -0.67
     Banking
    -0.65
    etta
    -0.64
     OLED
    -0.64
     November
    -0.63
     deren
    -0.63
     needy
    -0.63
     código
    -0.62
    POSITIVE LOGITS
    geometric
    0.73
    père
    0.69
    éz
    0.69
    Wiz
    0.68
    Garcia
    0.68
     tider
    0.68
    endencias
    0.67
    hawks
    0.66
     Melton
    0.66
    掉的
    0.65
    Activations Density 0.059%

    No Known Activations