© 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. 120
    Prev
    Next
    INDEX
    Explanations

    lora, Terracotta Army, code, columns

    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
    nt
    0.43
    ገል
    0.42
    ctu
    0.40
    सूस
    0.39
    Associated
    0.39
    난다
    0.39
    ಸ
    0.39
    nk
    0.38
    ankt
    0.38
    误
    0.38
    POSITIVE LOGITS
     impunity
    0.50
     parac
    0.44
     sharp
    0.42
     கூடிய
    0.41
     wherein
    0.40
    赜
    0.39
     enim
    0.39
     código
    0.38
     unsh
    0.38
     ひ
    0.38
    Activations Density 0.000%

    No Known Activations