© 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. 4176
    Prev
    Next
    INDEX
    Explanations

    introduces explanations and questions

    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
    특별시
    2.38
    ्स
    2.20
    lc
    2.05
    oo
    1.98
    اً
    1.95
    lle
    1.94
    eer
    1.87
    cribing
    1.84
    ્સ
    1.80
    tion
    1.73
    POSITIVE LOGITS
     внутрен
    2.05
    س
    2.00
    м
    1.85
    ча
    1.84
    ل
    1.83
    వరకు
    1.81
    ль
    1.77
    ج
    1.76
     cercana
    1.75
    লা
    1.70
    Activations Density 0.176%

    No Known Activations