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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70514
    Prev
    Next
    INDEX
    Explanations

    occupation details

    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
    甃
    -2.80
    鲎
    -2.59
    櫺
    -2.55
    遹
    -2.52
    鲞
    -2.52
    螄
    -2.50
    硨
    -2.33
    一旁
    -2.31
    埽
    -2.31
    HttpFoundation
    -2.28
    POSITIVE LOGITS
    ↵
    4.97
    0
    2.95
    </sup>
    2.73
     "";
    2.30
    </em>
    2.27
    </h4>
    2.22
     décédé
    2.17
    ”,
    2.14
     zweiter
    2.13
    ↵↵
    2.09
    Activations Density 0.004%

    No Known Activations