© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 53417
    Prev
    Next
    INDEX
    Explanations

    accessibility, vs, open source, surgery, linguistic mechanisms

    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_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
     deslig
    0.42
     accessory
    0.42
     natures
    0.41
     pairing
    0.41
    (
    0.40
     Exec
    0.40
     EXTER
    0.40
     drugstore
    0.39
     teachers
    0.39
    oxyd
    0.39
    POSITIVE LOGITS
     ivvu
    0.50
     oorlog
    0.49
    ዜ
    0.47
     हिटलर
    0.47
    युद्ध
    0.46
    𝓂
    0.46
     далі
    0.46
     सापेक्ष
    0.45
    表明
    0.45
    玧
    0.44
    Activations Density 0.002%

    No Known Activations