© 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. 61656
    Prev
    Next
    INDEX
    Explanations

    coverage, misappropriation, infringement

    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
    环节
    0.43
     الحديث
    0.43
    ：
    0.42
    𝚗
    0.41
     Charakter
    0.41
    一周
    0.41
    报告
    0.40
     একটা
    0.39
    方程
    0.39
    :
    0.39
    POSITIVE LOGITS
     cobertura
    0.48
     ಪ್ರ
    0.43
     bitmaps
    0.42
     sticky
    0.41
    щать
    0.41
    πι
    0.40
     DispatchQueue
    0.40
     покрытие
    0.40
     misappropri
    0.40
     infringement
    0.40
    Activations Density 0.017%

    No Known Activations