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. 7940
    Prev
    Next
    INDEX
    Explanations

    names followed by locations

    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
    Punjab
    -0.85
    Lorem
    -0.83
     notamment
    -0.80
     punctures
    -0.80
     Kosher
    -0.79
    Pentru
    -0.79
    ccn
    -0.78
    庁
    -0.78
     Ioan
    -0.78
     られる
    -0.78
    POSITIVE LOGITS
     via
    1.73
    via
    1.27
     retired
    1.19
     emailed
    1.13
     Via
    1.11
     address
    1.10
     vía
    1.09
     addresses
    1.08
    Via
    1.08
    retired
    1.05
    Activations Density 0.003%

    No Known Activations