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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 110955
    Prev
    Next
    INDEX
    Explanations

    forum post identifiers

    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_40_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
     знаем
    0.38
    स्म
    0.37
    }.${
    0.37
    λει
    0.37
    ripty
    0.37
    得知
    0.37
    স্ম
    0.36
    nameof
    0.36
    ?[
    0.35
     libsql
    0.35
    POSITIVE LOGITS
     comment
    0.53
     komentar
    0.48
     hooking
    0.47
     Comment
    0.45
    Comment
    0.45
     মন্ত
    0.45
     jumping
    0.43
     comentário
    0.42
     coment
    0.42
     jumps
    0.41
    Activations Density 0.002%

    No Known Activations