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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27644
    Prev
    Next
    INDEX
    Explanations

    Dave Davis, Prenatal, XML, Simple Polar

    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
    他有
    -1.00
    simage
    -1.00
    ߫
    -0.97
    četně
    -0.96
    atelier
    -0.96
     pö
    -0.95
     mají
    -0.94
     Incluye
    -0.94
    了一口
    -0.93
    СЫ
    -0.92
    POSITIVE LOGITS
     and
    1.45
    }_{
    1.07
     یا
    0.97
     теперь
    0.93
    ↵↵
    0.93
     này
    0.89
    .')
    0.88
    ‌آ
    0.82
     или
    0.82
    <0xA3>
    0.81
    Activations Density 0.000%

    No Known Activations