© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68815
    Prev
    Next
    INDEX
    Explanations

    world. wetland

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

    capturing, law, niche, rain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ссию
    0.47
     distribuição
    0.46
     centerX
    0.45
    jsdelivr
    0.45
    ການ
    0.45
    ﻛ
    0.44
    ло
    0.44
    ສະ
    0.44
    анали
    0.43
    鹌
    0.43
    POSITIVE LOGITS
    apeut
    0.56
    rett
    0.48
    irting
    0.48
    ด้อ
    0.48
    ridine
    0.47
    rtList
    0.46
    ttier
    0.46
    pada
    0.46
    bei
    0.45
     chois
    0.44
    Activations Density 0.000%

    No Known Activations