© 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. 65177
    Prev
    Next
    INDEX
    Explanations

    cruel

    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
    釦
    -2.73
    賔
    -2.56
    ৄ
    -2.56
    ୈ
    -2.44
    鲵
    -2.36
    đầm
    -2.34
    罣
    -2.34
    Зно
    -2.33
    Donativos
    -2.27
    ｄ
    -2.27
    POSITIVE LOGITS
    0
    3.63
    </h4>
    2.95
    .
    2.91
    7
    2.86
    <i>
    2.80
    an
    2.77
    3
    2.70
    </b>
    2.64
    8
    2.61
    that
    2.59
    Activations Density 0.002%

    No Known Activations