© 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. 241554
    Prev
    Next
    INDEX
    Explanations

    years of experience

    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
     சிறு
    0.50
     działalności
    0.50
     oby
    0.49
    śmy
    0.49
    쾨
    0.48
     wyt
    0.48
     systemu
    0.47
    ㅎ
    0.47
     الجه
    0.46
     yaşam
    0.46
    POSITIVE LOGITS
    ↵
    0.52
    affect
    0.50
    in
    0.46
    สัน
    0.45
     furrow
    0.44
     precincts
    0.44
    nucleus
    0.43
    addGroup
    0.42
     RIC
    0.42
     turnout
    0.42
    Activations Density 0.000%

    No Known Activations