© 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-262K
    7. 75722
    Prev
    Next
    INDEX
    Explanations

    retribution, determinism, changes

    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
     اجر
    0.48
     gewährleisten
    0.45
    QUESTIONS
    0.45
     〢
    0.44
     المدرسة
    0.43
    لمات
    0.42
     gewährle
    0.41
     mật
    0.40
     дві
    0.40
     použit
    0.40
    POSITIVE LOGITS
     dehuman
    0.45
     surface
    0.45
     entrop
    0.45
    갈
    0.44
     강력
    0.43
     Aqui
    0.43
     உருவாக
    0.42
     astrophysical
    0.42
     nowych
    0.42
     scream
    0.42
    Activations Density 0.002%

    No Known Activations