© 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. 31-GEMMASCOPE-2-RES-65K
    7. 55223
    Prev
    Next
    INDEX
    Explanations

    code with non-english words

    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_65k_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
    at
    0.88
    e
    0.80
    ing
    0.80
    ة
    0.73
    م
    0.72
    i
    0.69
    end
    0.69
    ek
    0.68
    en
    0.68
    y
    0.67
    POSITIVE LOGITS
     براي
    0.64
     сед
    0.64
     váy
    0.63
    렜
    0.62
     на
    0.61
    positroid
    0.61
    лық
    0.61
    <unused511>
    0.61
    <unused1070>
    0.60
     цик
    0.59
    Activations Density 0.007%

    No Known Activations