© 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. 41-GEMMASCOPE-2-RES-262K
    7. 65796
    Prev
    Next
    INDEX
    Explanations

    tPA

    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_all/layer_41_width_262k_l0_big
    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
    াহি
    0.46
    жо
    0.40
     కామె
    0.38
    tabControl
    0.36
    endant
    0.35
     Биз
    0.35
    abase
    0.35
    乇
    0.34
    iptic
    0.34
    omitem
    0.33
    POSITIVE LOGITS
     throm
    1.05
     fibrin
    1.03
     plas
    0.89
    fibr
    0.83
     fibr
    0.80
     Plas
    0.80
     clot
    0.75
     alte
    0.74
    Plas
    0.73
     uro
    0.71
    Activations Density 0.001%

    No Known Activations