© 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. 16-GEMMASCOPE-2-RES-262K
    7. 18160
    Prev
    Next
    INDEX
    Explanations

    any other/human

    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_16_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
    場合に
    0.60
     लीटर
    0.59
     కేసులు
    0.55
    ‌آ
    0.54
     Když
    0.54
     einigen
    0.53
    အတူ
    0.53
     ά
    0.51
    ذكر
    0.51
     Teilen
    0.51
    POSITIVE LOGITS
    ol
    0.75
     mobile
    0.59
    ok
    0.58
    nt
    0.56
     de
    0.56
     podcast
    0.55
     media
    0.54
     hari
    0.54
    !
    0.54
     festival
    0.53
    Activations Density 0.014%

    No Known Activations