© 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. 20745
    Prev
    Next
    INDEX
    Explanations

    serif fonts

    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
    を終
    -2.45
    ⩥
    -2.39
    筴
    -2.39
     refusé
    -2.31
    艄
    -2.28
     ส์
    -2.28
    躥
    -2.27
    轳
    -2.23
    榈
    -2.19
    奩
    -2.08
    POSITIVE LOGITS
    %
    2.63
    e
    2.58
    '
    2.55
    mathrm
    2.31
    ’
    2.22
    的
    2.17
    ''
    2.11
    琊
    2.08
    serif
    2.06
    “
    2.06
    Activations Density 0.001%

    No Known Activations