© 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. 40-GEMMASCOPE-2-RES-262K
    7. 131181
    Prev
    Next
    INDEX
    Explanations

    python imports from collections

    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_40_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
    귿
    0.43
    суа
    0.42
    Forgery
    0.42
    igheder
    0.41
     发布
    0.41
    dag
    0.40
    pipe
    0.40
     الكتاب
    0.40
    膩
    0.40
    เภท
    0.39
    POSITIVE LOGITS
     dul
    0.44
     naf
    0.39
    ovac
    0.39
     visuals
    0.38
     Conc
    0.38
     Uber
    0.37
     identified
    0.37
     twice
    0.37
     Iya
    0.37
     continental
    0.37
    Activations Density 0.000%

    No Known Activations