© 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. 212972
    Prev
    Next
    INDEX
    Explanations

    AI and definitions

    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
    collected
    0.41
    interests
    0.40
    attrs
    0.38
     アイ
    0.38
    inventory
    0.38
    itent
    0.38
     abgest
    0.38
     組
    0.38
    properties
    0.37
    electrons
    0.36
    POSITIVE LOGITS
     COE
    0.40
    娄
    0.40
    Ри
    0.39
     Genève
    0.39
     Федерации
    0.39
    俊
    0.39
    ².
    0.39
     হইয়৷
    0.38
     Andreev
    0.38
    केंद्र
    0.38
    Activations Density 0.000%

    No Known Activations