© 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. 219622
    Prev
    Next
    INDEX
    Explanations

    Meanwhile,

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

    meanwhile, in the meantime

    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
    i
    0.91
    ي
    0.77
    י
    0.76
    p
    0.69
    st
    0.65
    parameter
    0.63
    player
    0.62
    as
    0.61
    later
    0.60
    ן
    0.59
    POSITIVE LOGITS
     sèche
    0.70
     Fiziki
    0.67
     continúa
    0.66
    अब
    0.66
     Сак
    0.64
    িগ
    0.64
     dignidad
    0.64
     custodians
    0.62
     ساح
    0.61
    ູ່
    0.61
    Activations Density 0.007%

    No Known Activations