© 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. 48618
    Prev
    Next
    INDEX
    Explanations

    binary data and computation

    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
    (#
    0.48
    𝗳
    0.47
    =?
    0.47
    真正
    0.46
    actual
    0.46
    ;#
    0.46
    jl
    0.45
    arged
    0.45
    ld
    0.45
    '`
    0.45
    POSITIVE LOGITS
     Verwaltung
    0.52
     Works
    0.52
     Disbursements
    0.49
     Securities
    0.47
     Arbeiten
    0.47
     Repairs
    0.46
     bouw
    0.46
     Robust
    0.46
     Borough
    0.45
     skimming
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.