© 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. 71537
    Prev
    Next
    INDEX
    Explanations

    movement direction

    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
    -3.44
    8
    -2.98
    6
    -2.97
    4
    -2.91
    e
    -2.80
    7
    -2.63
    5
    -2.53
    3
    -2.50
    for
    -2.44
    9
    -2.38
    POSITIVE LOGITS
    辄
    2.67
    %;
    2.56
    %">
    2.45
    摇了
    2.42
     */
    2.42
    锜
    2.34
    ⬯
    2.28
    งิน
    2.27
    辚
    2.25
     веке
    2.23
    Activations Density 0.018%

    No Known Activations