© 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. 7843
    Prev
    Next
    INDEX
    Explanations

    Wien, tachometer

    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
    autogui
    -2.95
    埸
    -2.88
    ি
    -2.80
    他
    -2.75
     جدید
    -2.75
    橚
    -2.70
     插画
    -2.70
    ي
    -2.67
    鹮
    -2.66
     celebrates
    -2.64
    POSITIVE LOGITS
    ing
    3.17
     curtail
    2.83
     Utilizing
    2.69
    目的是
    2.67
    又被
    2.63
    I
    2.50
    翃
    2.50
     '
    2.50
    ization
    2.45
     Important
    2.42
    Activations Density 0.039%

    No Known Activations