© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11279
    Prev
    Next
    INDEX
    Explanations

    character

    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_40_width_16k_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
    पा
    0.50
    बि
    0.46
    ने
    0.46
    yı
    0.45
    야
    0.45
    єю
    0.44
    ব
    0.43
    று
    0.42
    সিক
    0.42
    ना
    0.42
    POSITIVE LOGITS
     Character
    0.71
     Charakter
    0.71
    istically
    0.69
    Character
    0.65
    ization
    0.60
    itics
    0.60
    izations
    0.54
    heets
    0.54
    istika
    0.52
    istical
    0.52
    Activations Density 0.108%

    No Known Activations