© 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. 97960
    Prev
    Next
    INDEX
    Explanations

    if, ., face, pricing, having

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

    explaining broad concepts

    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
    ຂໍ້ມ
    0.50
    kinetic
    0.48
     enticing
    0.47
    id
    0.44
    kite
    0.42
    wia
    0.42
    ӗ
    0.42
    il
    0.42
    openid
    0.42
     reclining
    0.42
    POSITIVE LOGITS
    较为
    0.52
     Porn
    0.49
     Pupil
    0.49
    骂
    0.48
    NotFoundError
    0.48
     уні
    0.47
     Никола
    0.47
    ：《
    0.45
    Consider
    0.44
    谱
    0.43
    Activations Density 0.000%

    No Known Activations