© 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. 15431
    Prev
    Next
    INDEX
    Explanations

    surname ancestors or siblings

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

    world population or groups

    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
    笂
    0.51
    ოვანი
    0.46
     에서
    0.46
    ന്വേഷ
    0.46
    에서는
    0.43
    county
    0.42
     hesab
    0.42
    itivos
    0.41
    extrémité
    0.40
    ूले
    0.40
    POSITIVE LOGITS
    idual
    0.43
     singing
    0.42
     задания
    0.40
     ngũ
    0.40
     kennt
    0.39
    ----
    0.38
     allgeme
    0.38
     ናቸው
    0.38
     giải
    0.37
    мон
    0.37
    Activations Density 0.000%

    No Known Activations