© 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. 44280
    Prev
    Next
    INDEX
    Explanations

    cameron's avatar, SPC macro

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

    action and outcome

    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
     A
    0.73
    in
    0.68
    A
    0.63
    b
    0.62
    -
    0.62
     Avila
    0.61
     Ar
    0.61
     Bri
    0.60
     Agr
    0.60
    u
    0.60
    POSITIVE LOGITS
    usingCamera
    0.57
    সংখ্য
    0.54
     характеристи
    0.54
     এগিয়ে
    0.52
     итоге
    0.52
    Celltype
    0.51
     മിക
    0.50
    UTICAL
    0.49
     সিদ্ধান্ত
    0.49
    StarGo
    0.49
    Activations Density 0.000%

    No Known Activations