© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 30722
    Prev
    Next
    INDEX
    Explanations

    technical acronyms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ја
    0.75
    lections
    0.71
    children
    0.71
    oji
    0.70
    oj
    0.70
    ה
    0.70
    も
    0.69
     ۴
    0.68
    اً
    0.68
    މ
    0.68
    POSITIVE LOGITS
     dedu
    0.65
     metagen
    0.55
     재생
    0.54
     reshape
    0.53
     redraw
    0.53
     repaint
    0.53
     decar
    0.53
     marina
    0.52
     syntactic
    0.52
     homestead
    0.52
    Activations Density 0.070%

    No Known Activations