© 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. 35973
    Prev
    Next
    INDEX
    Explanations

    . And

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

    roles and belonging

    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
    платы
    0.55
    规则
    0.51
     regole
    0.49
     규칙
    0.49
    商家
    0.49
    满满
    0.48
    痞
    0.48
    רק
    0.47
     వచ్చింది
    0.47
    unordered
    0.46
    POSITIVE LOGITS
     partake
    0.50
     incidentally
    0.47
     occupy
    0.46
     belong
    0.46
     belonging
    0.44
     belonged
    0.44
     étude
    0.44
     emanc
    0.44
     humanities
    0.43
     journalism
    0.43
    Activations Density 0.000%

    No Known Activations