© 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. 10-GEMMASCOPE-RES-131K
    4. 119830
    Prev
    Next
    INDEX
    Explanations

    Verizon Wireless, drawstring, Denied, shortcut, Crow

    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
    en
    -2.03
    </u>
    -2.03
    </b>
    -1.87
    ');
    
    -1.84
    ')}}
    -1.77
    ᡵ
    -1.74
    </h5>
    -1.71
    觊
    -1.69
    er
    -1.68
     }}$
    -1.67
    POSITIVE LOGITS
    舠
    1.92
    鲧
    1.87
    ,,
    1.73
    s
    1.72
     reembolso
    1.70
    他的
    1.68
    髕
    1.67
     sebagainya
    1.66
    得多
    1.65
     μεγά
    1.63
    Activations Density 0.003%

    No Known Activations