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. 110143
    Prev
    Next
    INDEX
    Explanations

    following "2"

    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
     what
    -1.20
    What
    -1.11
    に行ってきました
    -0.97
     new
    -0.94
     tiny
    -0.91
    }}>
    -0.91
     FOR
    -0.88
    ****
    -0.88
     Rettung
    -0.85
    нял
    -0.85
    POSITIVE LOGITS
    олові
    1.04
    実は
    0.99
     hende
    0.98
    ाली
    0.97
    もありますが
    0.95
     الجيش
    0.94
     rând
    0.93
    签
    0.93
    ász
    0.92
     furthermore
    0.92
    Activations Density 0.037%

    No Known Activations