© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 251352
    Prev
    Next
    INDEX
    Explanations

    eye catching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     multitudes
    0.57
    \
    0.56
    isasi
    0.53
     سوری
    0.52
    تي
    0.52
    벍
    0.51
    менить
    0.50
    (
    0.50
    ação
    0.48
     vini
    0.48
    POSITIVE LOGITS
    eye
    0.92
    EY
    0.88
     eye
    0.86
    Eye
    0.83
     Eye
    0.83
     EYE
    0.82
    眼
    0.65
    大
    0.62
     눈
    0.61
     Ey
    0.58
    Activations Density 0.095%

    No Known Activations