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. 61
    Prev
    Next
    INDEX
    Explanations

    Olivier van

    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
    าสตร์
    -0.81
     strapless
    -0.78
    вик
    -0.77
     Polit
    -0.76
    际
    -0.75
    intval
    -0.73
     ====
    -0.72
     Holiness
    -0.71
     ------------
    -0.69
    brasil
    -0.69
    POSITIVE LOGITS
     Funding
    0.99
     funding
    0.97
     announcer
    0.85
     ANNOUNC
    0.82
    Funding
    0.82
     woman
    0.81
    funded
    0.80
     funded
    0.75
     fund
    0.73
    ♪
    0.71
    Activations Density 0.005%

    No Known Activations