© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 119529
    Prev
    Next
    INDEX
    Explanations

    separately before

    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
     lowers
    0.43
     कहते
    0.40
     OPTIONS
    0.39
     baixo
    0.39
     KILL
    0.39
     Fonte
    0.38
     baixa
    0.38
    워
    0.37
    opts
    0.37
     flakes
    0.37
    POSITIVE LOGITS
    zym
    0.39
    ThemeOverlay
    0.38
    SpringMVCProject
    0.38
    tiene
    0.38
    ോഷ്യ
    0.37
    FlashValue
    0.37
    ntgen
    0.36
    icione
    0.36
    AfterTax
    0.36
    tele
    0.35
    Activations Density 0.000%

    No Known Activations