© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58823
    Prev
    Next
    INDEX
    Explanations

    pulsation, Rana, Cain, bip, snd

    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
    0
    -4.09
    1
    -3.53
    </h4>
    -3.39
     ‘
    -3.23
    9
    -3.02
    3
    -2.75
    6
    -2.70
    Now
    -2.67
    4
    -2.67
    ”
    -2.56
    POSITIVE LOGITS
    硨
    3.22
    柃
    2.97
    謌
    2.89
    孭
    2.80
    蕷
    2.67
    料
    2.63
    鶿
    2.56
    ズニー
    2.52
     вернулся
    2.48
    👸
    2.48
    Activations Density 0.008%

    No Known Activations