© 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. 6592
    Prev
    Next
    INDEX
    Explanations

    press Enter or key

    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
    ا
    2.88
    ва
    2.31
    да
    2.30
    い
    2.25
    ت
    2.22
    ı
    2.22
    ੁ
    2.20
    od
    2.09
    ak
    2.09
    タ
    1.97
    POSITIVE LOGITS
     écrite
    1.84
    ges
    1.72
    ల
    1.72
    くちゃ
    1.71
    doctoral
    1.70
    MaxPool
    1.70
     Crear
    1.70
    urized
    1.70
    singular
    1.67
    intégr
    1.66
    Activations Density 0.039%

    No Known Activations