© 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. 135621
    Prev
    Next
    INDEX
    Explanations

    school.during one.underpinned by.stirrer available.concrete where.plus any.bar soap

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

    faster growth or effectiveness

    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
     trẻ
    0.50
    ৪৭
    0.48
     आंगन
    0.46
    artigen
    0.46
    ,-
    0.45
     பணியாற்ற
    0.45
    萜
    0.44
     họp
    0.44
     young
    0.43
    ;-
    0.43
    POSITIVE LOGITS
     anot
    0.47
    赚钱
    0.46
     propo
    0.44
     journ
    0.43
    渣
    0.42
    ليا
    0.42
    титься
    0.41
    ApiKey
    0.41
    لي
    0.40
    骡
    0.40
    Activations Density 0.001%

    No Known Activations