© 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. 8157
    Prev
    Next
    INDEX
    Explanations

    languages from different countries

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

    deliberately nonstandard or distorted text forms—such as cutesy/UwU speech, omitted letters, hyphenated/fractured words, and URL/domain fragments.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ”
    0.15
    」
    0.12
    у
    0.12
    other
    0.12
     Editar
    0.12
    и
    0.12
    they
    0.12
    ;
    0.12
    си
    0.12
    о
    0.11
    POSITIVE LOGITS
     ombil
    0.14
     augmenter
    0.14
    资产
    0.13
    mW
    0.13
     tumeurs
    0.13
    लट्
    0.13
     mécanismes
    0.12
     bactéries
    0.12
     ausschließlich
    0.12
    Affine
    0.12
    Activations Density 0.192%

    No Known Activations