© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 682
    Prev
    Next
    INDEX
    Explanations

    entire/whole followed by noun

    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_10/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
    </b>
    -1.73
    März
    -1.54
     aislada
    -1.45
     什么
    -1.45
     jednym
    -1.45
     Betrachtung
    -1.44
     男人
    -1.43
     tivi
    -1.41
     صفح
    -1.41
    遢
    -1.40
    POSITIVE LOGITS
     what
    1.66
     numerous
    1.55
     chilen
    1.52
     information
    1.49
     an
    1.49
     several
    1.48
     all
    1.48
    t
    1.48
    </em>
    1.45
     Not
    1.44
    Activations Density 0.012%

    No Known Activations