© 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. 211186
    Prev
    Next
    INDEX
    Explanations

    through such

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

    goal is to write

    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
    畐
    0.53
     Đến
    0.50
    ｑ
    0.48
    بین
    0.47
    गत
    0.47
     viaj
    0.46
    gios
    0.46
    quy
    0.45
    وص
    0.45
    ចូល
    0.45
    POSITIVE LOGITS
    {}
    0.49
     doughnuts
    0.48
     misunderstand
    0.48
     ether
    0.46
    %;
    0.45
     mentor
    0.45
    ,
    0.45
     manne
    0.44
     align
    0.43
    🍩
    0.43
    Activations Density 0.002%

    No Known Activations