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. 8602
    Prev
    Next
    INDEX
    Explanations

    legal documents and HTML

    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
     then
    -1.13
    Ώ
    -1.09
     its
    -1.07
    Trichloroethane
    -1.07
    遠い
    -1.06
    際は
    -1.05
    際には
    -1.02
    hagic
    -1.02
     価格
    -1.02
     it
    -1.01
    POSITIVE LOGITS
    で
    1.17
    }\}
    1.13
    カップ
    1.02
    taglio
    1.00
    が
    0.97
    を
    0.96
    は
    0.96
    combs
    0.94
    ircut
    0.94
     isKindOfClass
    0.94
    Activations Density 0.011%

    No Known Activations