© 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. 75150
    Prev
    Next
    INDEX
    Explanations

    skip to main content

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

    skip to sections or inline

    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
     biochemical
    0.40
     خون
    0.40
    >`
    0.39
     warehouse
    0.39
     المعل
    0.39
    destructive
    0.38
     arach
    0.38
    倉庫
    0.38
    BlackElo
    0.38
     isinstance
    0.38
    POSITIVE LOGITS
    skip
    0.43
     первый
    0.43
    수상
    0.42
     skips
    0.41
     skip
    0.40
     skipped
    0.39
     문제는
    0.38
    ‏:‏
    0.37
    상은
    0.37
    לה
    0.37
    Activations Density 0.001%

    No Known Activations