© 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-16K
    7. 1038
    Prev
    Next
    INDEX
    Explanations

    conditional structures

    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_16k_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
    ä
    0.89
    č
    0.79
     Dzięki
    0.76
    it
    0.69
    oretically
    0.68
    á
    0.68
    ajā
    0.67
     größere
    0.67
     गरेका
    0.67
     وبين
    0.67
    POSITIVE LOGITS
    ん
    0.83
    ার
    0.82
    ן
    0.73
    亠
    0.66
    lubridate
    0.64
    р
    0.64
    oubl
    0.62
    <0x80>
    0.62
    ר
    0.60
    면
    0.60
    Activations Density 0.263%

    No Known Activations