© 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. 31-GEMMASCOPE-2-RES-262K
    7. 99919
    Prev
    Next
    INDEX
    Explanations

    function arguments, dates, origin, scale

    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_31_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
    ской
    0.50
    вый
    0.50
    ومه
    0.47
    дым
    0.47
     enthalpy
    0.46
    рона
    0.46
    𝗩
    0.45
    𝐯
    0.45
    вые
    0.44
    сных
    0.44
    POSITIVE LOGITS
    erm
    0.48
     для
    0.47
     למ
    0.47
     für
    0.44
     بح
    0.44
     Shir
    0.43
     لیک
    0.43
     মু
    0.43
     بين
    0.42
     για
    0.41
    Activations Density 0.005%

    No Known Activations