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. 7882
    Prev
    Next
    INDEX
    Explanations

    Pampanga, Pinoy, Pangani, National Assembly, Šeduva, Bassam

    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
     industries
    -0.81
     IN
    -0.78
     reel
    -0.76
     emel
    -0.75
     den
    -0.75
     vas
    -0.75
     է
    -0.74
     perilaku
    -0.73
     cel
    -0.73
     Institution
    -0.73
    POSITIVE LOGITS
    assemblée
    0.84
     Sehingga
    0.84
     加盟
    0.81
    known
    0.81
    Maybe
    0.80
    ၵ
    0.80
    Should
    0.80
    Leben
    0.80
     known
    0.79
    Several
    0.79
    Activations Density 0.000%

    No Known Activations