© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8547
    Prev
    Next
    INDEX
    Explanations

    cozy sigh

    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
    ند
    3.08
    น
    3.08
    ians
    2.88
    mal
    2.73
    son
    2.70
    ni
    2.66
    ින්
    2.61
    st
    2.58
    m
    2.56
    ם
    2.56
    POSITIVE LOGITS
    ি
    2.77
    で
    2.72
    ीकरण
    2.28
    ी
    2.19
    에서
    2.03
    ん
    2.03
    くちゃ
    1.98
    ்ய
    1.97
    ளில்
    1.95
    ेन
    1.95
    Activations Density 0.259%

    No Known Activations