© 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. 31-GEMMASCOPE-2-RES-262K
    7. 5118
    Prev
    Next
    INDEX
    Explanations

    Linux kernel

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

    capitalized proper nouns and titles—names of people, places, products/technologies, and media works.

    oai_token-act-pair · gpt-5Triggered by @yooniel31
    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
    ل
    0.26
    y
    0.22
    l
    0.20
    lty
    0.19
    el
    0.18
    zelfde
    0.18
     dieser
    0.18
     deleter
    0.17
     HTMLSc
    0.17
     radiometric
    0.17
    POSITIVE LOGITS
     యొక్క
    0.22
     törté
    0.20
    <unused2138>
    0.20
    owników
    0.20
     있는
    0.19
     kwenye
    0.19
    에
    0.19
     bhikkhu
    0.19
     வரலா
    0.19
    ეთის
    0.19
    Activations Density 0.747%

    No Known Activations