Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8855
    Prev
    Next
    INDEX
    Explanations

    input/output and conjunctions

    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
     العرب
    -0.80
    ...-
    -0.77
    zemu
    -0.76
    ζ
    -0.75
    -“
    -0.73
     Woodlands
    -0.73
     pasir
    -0.72
    (“
    -0.71
    AGE
    -0.71
    ierta
    -0.70
    POSITIVE LOGITS
    與
    0.97
     and
    0.94
    钝
    0.92
     sentada
    0.89
     či
    0.87
     or
    0.87
    与
    0.85
    hütte
    0.83
    否
    0.83
    Or
    0.83
    Activations Density 0.191%

    No Known Activations