© 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. 30331
    Prev
    Next
    INDEX
    Explanations

    why questions and specific lists

    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
     exuberant
    0.57
     luscious
    0.55
     confortable
    0.54
     instinctive
    0.52
     crazy
    0.51
     xix
    0.51
     x
    0.51
     prolific
    0.51
     rude
    0.50
     homely
    0.50
    POSITIVE LOGITS
    名单
    0.54
    和社会
    0.45
    逘
    0.45
    防控
    0.45
    าน
    0.45
    调度
    0.45
    обо
    0.44
    Compiled
    0.44
    这将
    0.44
    িস
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.