© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 193823
    Prev
    Next
    INDEX
    Explanations

    explanations of why or how

    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_40_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
     sbParams
    0.41
     solito
    0.39
    鏟
    0.38
     swaying
    0.38
    ﾋ
    0.37
     radiologists
    0.37
     thorium
    0.37
     পুর্ব
    0.37
     брон
    0.37
     ե
    0.36
    POSITIVE LOGITS
     cien
    0.46
    chrono
    0.41
    increases
    0.40
     Increases
    0.39
     jedes
    0.38
     Antibody
    0.38
     lia
    0.38
     Fluid
    0.37
     menyer
    0.37
     Micros
    0.37
    Activations Density 0.001%

    No Known Activations