© 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. 179772
    Prev
    Next
    INDEX
    Explanations

    occupations, pink, and Dixon's

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

    digits, choosing, parameters

    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
     thành
    0.59
     Matrices
    0.49
     dön
    0.48
     Grün
    0.45
     distancing
    0.45
     Galilee
    0.45
    ပြန်
    0.43
    成
    0.43
    در
    0.42
     duyệt
    0.42
    POSITIVE LOGITS
     pink
    0.51
     occupa
    0.46
     勺
    0.45
    ccccc
    0.44
    Ꭺ
    0.44
     occupations
    0.44
     occupation
    0.43
    PINK
    0.43
     गुलाबी
    0.42
    pink
    0.42
    Activations Density 0.000%

    No Known Activations