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. 8526
    Prev
    Next
    INDEX
    Explanations

    Philippine local elections

    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
     on
    -1.00
    Պ
    -0.93
    ??
    -0.93
    挨拶
    -0.91
     weirdly
    -0.89
     comprehensive
    -0.88
     gæ
    -0.88
     retarded
    -0.85
     what
    -0.85
     seemingly
    -0.85
    POSITIVE LOGITS
    maybe
    1.13
    perhaps
    1.04
    possibly
    0.98
     usando
    0.98
     anschließend
    0.97
    NSE
    0.96
    攙
    0.96
    ఱ
    0.94
    послед
    0.91
    悻
    0.90
    Activations Density 0.001%

    No Known Activations