© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3636
    Prev
    Next
    INDEX
    Explanations

    join method parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ي
    1.48
     thuốc
    1.41
     thuring
    1.39
    ème
    1.38
     httpServer
    1.34
    斛
    1.32
     Página
    1.29
    িয়ার
    1.27
     olefins
    1.27
    "',
    1.26
    POSITIVE LOGITS
    م
    2.11
    ει
    2.08
    ن
    1.94
    ر
    1.72
    یا
    1.68
    ם
    1.66
    m
    1.58
    n
    1.57
    يد
    1.54
    ع
    1.53
    Activations Density 0.028%

    No Known Activations