© 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. 100887
    Prev
    Next
    INDEX
    Explanations

    topics, concepts, or entities

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

    enter, handling, position

    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
    obytes
    0.51
    ceu
    0.50
    其他
    0.49
    색
    0.49
    地形
    0.49
    대의
    0.48
    that
    0.48
    feature
    0.48
    出
    0.48
    fehl
    0.47
    POSITIVE LOGITS
     paediatric
    0.57
     neoliberal
    0.46
     показывать
    0.46
     barbit
    0.45
     nostalgic
    0.44
     rear
    0.44
     storyline
    0.44
     curriculum
    0.43
     arct
    0.43
     sanitizer
    0.42
    Activations Density 0.000%

    No Known Activations