© 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. 84843
    Prev
    Next
    INDEX
    Explanations

    fiancé, freelancer, glioma

    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
    扨
    -3.06
    ஂ
    -2.73
     民宿
    -2.66
    ⁈
    -2.66
    哢
    -2.58
    踅
    -2.56
     チャーム
    -2.52
     Geschä
    -2.52
    啣
    -2.48
     クルー
    -2.47
    POSITIVE LOGITS
     "
    3.19
    (
    3.14
    2
    2.64
    h
    2.61
    A
    2.61
     /
    2.53
    ''
    2.48
    e
    2.44
     f
    2.39
    up
    2.36
    Activations Density 0.003%

    No Known Activations