© 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. 855
    Prev
    Next
    INDEX
    Explanations

    data transfer objects

    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
    1
    -3.61
    3
    -3.14
    ;
    -3.14
    -2.89
    "
    -2.80
    </i>
    -2.77
    6
    -2.77
    4
    -2.72
    7
    -2.67
    ↵
    -2.59
    POSITIVE LOGITS
    怿
    2.86
     nji
    2.73
    釤
    2.69
    銫
    2.66
     teléfonos
    2.56
    อื่น
    2.56
     suoi
    2.56
    齶
    2.53
    獃
    2.53
    蠲
    2.53
    Activations Density 0.001%

    No Known Activations