© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60143
    Prev
    Next
    INDEX
    Explanations

    high and following words

    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
     “
    -2.06
     (“
    -1.91
    -
    -1.79
    <
    -1.69
    ,”
    -1.65
    .’
    -1.64
     эффектив
    -1.62
    </h3>
    -1.61
    —”
    -1.59
    即是
    -1.58
    POSITIVE LOGITS
     vicino
    1.92
    洐
    1.90
    ﻊ
    1.73
    high
    1.72
    鲵
    1.70
    лась
    1.70
     wens
    1.68
    ровала
    1.65
     furent
    1.63
     penchant
    1.63
    Activations Density 0.073%

    No Known Activations