© 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. 33191
    Prev
    Next
    INDEX
    Explanations

    service, last, Rep

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

    protocols involve

    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
     }^{[
    0.53
     Frankly
    0.48
     vividly
    0.48
     Peterson
    0.46
     Smith
    0.46
     ultimately
    0.45
    oster
    0.45
     orderly
    0.45
     {[
    0.45
    '[
    0.45
    POSITIVE LOGITS
    یک
    0.55
     finans
    0.52
    โย
    0.49
    ربه
    0.47
     vybaven
    0.46
     ظ
    0.46
     lekk
    0.44
    ت
    0.43
    冏
    0.43
    ט
    0.43
    Activations Density 0.000%

    No Known Activations