© 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. 3960
    Prev
    Next
    INDEX
    Explanations

    baccarat, bacillus

    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
     Catawiki
    0.42
    Radiux
    0.41
     Δεν
    0.40
     』
    0.39
    📰
    0.39
    pkins
    0.39
     肉
    0.38
     تصویر
    0.38
    strMeal
    0.38
     게시
    0.38
    POSITIVE LOGITS
     B
    0.46
     bac
    0.45
    bac
    0.44
    Bac
    0.43
     Bac
    0.40
    ђа
    0.39
     Bacillus
    0.38
     fixed
    0.38
     бъ
    0.38
    agiarism
    0.38
    Activations Density 0.070%

    No Known Activations