© 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. 44656
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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
    ࿙
    -1.70
    蚡
    -1.69
     For
    -1.67
     allerdings
    -1.57
    colgante
    -1.52
    艽
    -1.50
    芫
    -1.48
    ௅
    -1.47
     Darstellung
    -1.45
    鵟
    -1.44
    POSITIVE LOGITS
    F
    2.20
    S
    2.05
    K
    2.03
    V
    2.02
    u
    1.94
    P
    1.84
    !”
    1.82
    J
    1.82
    U
    1.78
    釹
    1.78
    Activations Density 0.012%

    No Known Activations