© 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. 65184
    Prev
    Next
    INDEX
    Explanations

    names and specific words

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

    Japanese particles

    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
    l
    0.71
    k
    0.70
    il
    0.67
     A
    0.67
    r
    0.66
    a
    0.66
    ä
    0.62
    y
    0.58
    isinde
    0.57
    ig
    0.56
    POSITIVE LOGITS
    도
    0.72
    在
    0.72
    も
    0.71
     in
    0.69
    です
    0.64
    で
    0.62
    ও
    0.61
    は
    0.59
    が
    0.59
     في
    0.57
    Activations Density 0.012%

    No Known Activations