© 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. 57684
    Prev
    Next
    INDEX
    Explanations

    small to health

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

    counting analyticsestimation requiredefendant companytrimester labelsdeveloper intent

    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
    in
    0.57
    ci
    0.45
    o
    0.43
    p
    0.43
    ave
    0.43
    Whatever
    0.43
    r
    0.43
    ").
    0.42
    ")[
    0.42
    re
    0.42
    POSITIVE LOGITS
     karate
    0.54
     kriminal
    0.54
    বিষ
    0.54
    И
    0.52
     машиналарын
    0.50
     bora
    0.50
    गारी
    0.50
     kakak
    0.49
    лан
    0.48
    કિસ્
    0.48
    Activations Density 0.000%

    No Known Activations