© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11064
    Prev
    Next
    INDEX
    Explanations

    gnu services, guix packages

    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
     स्थानिक
    0.43
     หน่อย
    0.42
    ക്കണം
    0.40
     डोनाल्ड
    0.39
    犟
    0.39
     Fachwerk
    0.38
    ชุม
    0.38
    らっしゃる
    0.38
     ازيكم
    0.37
    Maf
    0.37
    POSITIVE LOGITS
    Limits
    0.43
    酮
    0.42
     limits
    0.42
    limits
    0.42
     lub
    0.39
    开
    0.39
     $$
    0.39
     unw
    0.39
     Limits
    0.38
    loss
    0.38
    Activations Density 0.000%

    No Known Activations