© 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. 95339
    Prev
    Next
    INDEX
    Explanations

    debt status and management

    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
    __":
    -2.38
    阄
    -2.30
     них
    -2.19
     warmen
    -2.17
     he
    -2.16
    ご利用
    -2.14
    );
    -2.09
    澇
    -2.08
    的一天
    -2.08
    ll
    -2.06
    POSITIVE LOGITS
     nuova
    2.27
    "-"
    2.19
    ❣
    2.11
     himmel
    2.02
    用
    1.97
    вший
    1.94
    <bos>
    1.93
    蟊
    1.91
    😇
    1.91
    wwwwwwww
    1.90
    Activations Density 0.005%

    No Known Activations