© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185206
    Prev
    Next
    INDEX
    Explanations

    prices and dates

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

    names following ChatGPT

    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
    Negative Logits
     ribu
    0.54
    ،
    0.49
    voor
    0.47
    dari
    0.46
     جوس
    0.45
    cí
    0.45
     duvar
    0.44
     ตุลาคม
    0.44
    晟
    0.44
    库存
    0.44
    POSITIVE LOGITS
     prioritizing
    0.51
    Gay
    0.47
     Gay
    0.47
     Year
    0.46
     Kohli
    0.46
     efficacious
    0.45
     Bonjour
    0.45
     chatting
    0.44
     Chance
    0.44
     allocating
    0.44
    Activations Density 0.000%

    No Known Activations