© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1519
    Prev
    Next
    INDEX
    Explanations

    ordinary or traditional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     ügy
    1.83
    '
    1.80
     Дата
    1.79
    딧
    1.76
    Im
    1.72
    不僅
    1.71
     című
    1.70
    inerary
    1.69
    ’
    1.68
     Includes
    1.68
    POSITIVE LOGITS
    普通の
    2.49
    通常の
    2.29
     normalen
    2.26
    传统的
    2.22
     normale
    2.22
    传统
    2.13
     tradicionales
    2.10
     traditional
    2.08
     normales
    2.04
    一般的な
    2.00
    Activations Density 0.697%

    No Known Activations