© 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. 6045
    Prev
    Next
    INDEX
    Explanations

    user turn markers

    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
    즉
    1.04
    า
    0.93
    ל
    0.93
    愊
    0.93
    లోని
    0.91
    ið
    0.90
    норийска
    0.89
     Ā
    0.88
     profusely
    0.88
    ılarak
    0.88
    POSITIVE LOGITS
    te
    1.22
     judíos
    1.14
     Sebelumnya
    1.13
     cristianos
    1.13
     questões
    1.10
    0
    1.09
     Não
    1.07
     não
    1.05
    ?'
    1.05
     afiliados
    1.04
    Activations Density 0.006%

    No Known Activations