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. 8461
    Prev
    Next
    INDEX
    Explanations

    5 bit sequences

    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
     without
    -1.04
     completely
    -1.03
     very
    -1.00
     just
    -0.99
     entirely
    -0.96
    嬰
    -0.94
     очень
    -0.94
     what
    -0.93
     варіан
    -0.91
     sehr
    -0.91
    POSITIVE LOGITS
     DOWN
    0.92
     dow
    0.91
    dow
    0.88
     ndani
    0.85
     declaração
    0.83
     verborgen
    0.82
     temprano
    0.81
    瞅
    0.81
    Chi
    0.80
    inib
    0.80
    Activations Density 0.002%

    No Known Activations