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. 8449
    Prev
    Next
    INDEX
    Explanations

    code language labels

    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
     gravy
    -0.88
    ostar
    -0.74
     obviously
    -0.74
     what
    -0.73
     shook
    -0.73
     ограни
    -0.72
     fantasia
    -0.71
     described
    -0.70
     principi
    -0.69
     Alamofire
    -0.68
    POSITIVE LOGITS
     label
    0.90
     labels
    0.86
     jargon
    0.84
     cubrir
    0.82
    LBL
    0.82
     phrase
    0.81
     term
    0.79
     samlet
    0.77
    PLEASE
    0.77
     lbl
    0.77
    Activations Density 0.018%

    No Known Activations