© 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. 135593
    Prev
    Next
    INDEX
    Explanations

    ensuring that, may damage, FL snake

    np_acts-logits-general · gemini-2.5-flash-lite

    vertical, not run, failed, present, skill, building

    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
     opi
    0.50
    iniai
    0.48
    EY
    0.47
     dimost
    0.46
    isasi
    0.46
     ocz
    0.45
    ן
    0.44
     jaz
    0.44
    เป
    0.44
     buah
    0.44
    POSITIVE LOGITS
    rotation
    0.56
    ريم
    0.52
    regarding
    0.50
     Đến
    0.49
    ρούν
    0.47
    véd
    0.46
     Ramón
    0.46
     fundamentales
    0.45
    getWidth
    0.45
    塵
    0.45
    Activations Density 0.000%

    No Known Activations