© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40912
    Prev
    Next
    INDEX
    Explanations

    special action terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝙀
    0.49
    као
    0.48
    igneur
    0.48
    depending
    0.48
    кен
    0.47
    ütfen
    0.46
    餞
    0.46
    وامی
    0.45
    зне
    0.45
    던
    0.45
    POSITIVE LOGITS
     Diagn
    0.48
     Tisch
    0.45
     ODE
    0.45
     Narr
    0.45
     Cafe
    0.43
     Bets
    0.43
     therapist
    0.43
     humanities
    0.42
     R
    0.42
     café
    0.42
    Activations Density 0.001%

    No Known Activations