© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68242
    Prev
    Next
    INDEX
    Explanations

    location and organization

    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_22/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
    ****
    -1.16
    コチラ
    -1.07
    </b>
    -1.05
    関連リンク
    -1.05
     предпочита
    -1.04
     Væ
    -1.04
    难怪
    -1.03
    </em>
    -1.00
    %@",
    -1.00
     galaxia
    -1.00
    POSITIVE LOGITS
     וכן
    1.12
     locura
    1.05
    UIFont
    1.05
    িতে
    1.04
     barva
    0.99
     oči
    0.98
    期间
    0.96
    Zdra
    0.93
    losis
    0.92
     and
    0.91
    Activations Density 0.050%

    No Known Activations