© 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. 151196
    Prev
    Next
    INDEX
    Explanations

    app, ip, and util usage

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

    direct access to global leaders

    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
     oldCount
    0.52
     deprec
    0.50
     automorphisms
    0.49
     TestAvg
    0.48
     kosakata
    0.47
     Alloy
    0.47
    Კ
    0.47
     valu
    0.47
     analysts
    0.46
    ζε
    0.46
    POSITIVE LOGITS
    0.51
    利用
    0.47
    util
    0.44
    APP
    0.44
    catch
    0.43
    ai
    0.42
    IP
    0.41
    する
    0.41
    prop
    0.40
    by
    0.40
    Activations Density 0.000%

    No Known Activations