© 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. 4027
    Prev
    Next
    INDEX
    Explanations

    laxatives, logical, often, removes

    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
    ాలయ
    0.41
     compiler
    0.41
     Perkenalkan
    0.41
     setInterval
    0.40
     Thumbnail
    0.40
     Rea
    0.39
     murderous
    0.39
    謢
    0.39
     Meister
    0.38
     boul
    0.38
    POSITIVE LOGITS
    rightsquigarrow
    0.44
    ĐT
    0.43
    အတ
    0.43
    至少
    0.42
    选择
    0.40
    ZE
    0.40
    资源
    0.40
    bang
    0.39
    取消
    0.39
    eligible
    0.39
    Activations Density 0.000%

    No Known Activations