© 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. 55127
    Prev
    Next
    INDEX
    Explanations

    options granted

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

    internet, until, option, Ver, ul, 0, optimizer, varnish, with

    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
     яс
    0.43
     sections
    0.41
     ELEMENT
    0.41
     чы
    0.40
     ку
    0.40
    霎
    0.40
    蜱
    0.39
     це
    0.38
     Element
    0.38
     Sometimes
    0.38
    POSITIVE LOGITS
    yearly
    0.51
    道を
    0.50
     इकट
    0.49
     corriendo
    0.48
     Jahre
    0.48
    per
    0.48
    into
    0.48
    μαστε
    0.48
    eduanya
    0.47
    cohort
    0.46
    Activations Density 0.000%

    No Known Activations