© 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. 12403
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens from source code (programming identifiers, API/library names, code keywords and other code-specific tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    ठभे
    0.42
     paddingTop
    0.41
     pea
    0.41
    rollup
    0.41
     Purification
    0.40
     contenus
    0.40
    粑
    0.40
     باستخدام
    0.40
    Feeding
    0.40
    Establishing
    0.39
    POSITIVE LOGITS
    ഞ്ഞി
    0.43
     JW
    0.41
     criticised
    0.40
    ქ
    0.40
    INTS
    0.39
    etzes
    0.39
     düz
    0.37
    JW
    0.37
     TSP
    0.37
     اللَّ
    0.37
    Activations Density 3.423%

    No Known Activations