© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3333
    Prev
    Next
    INDEX
    Explanations

    specific to context

    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_24_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
     একটা
    0.79
     అనే
    0.77
     слегка
    0.77
     일이
    0.75
     പോക
    0.74
    ၌
    0.72
     jemand
    0.72
    !।
    0.71
    <0x19>
    0.70
    ੱਕ
    0.70
    POSITIVE LOGITS
    the
    0.85
     which
    0.74
    sthe
    0.72
    その他
    0.70
     The
    0.68
     PI
    0.68
     the
    0.67
     including
    0.66
     pertaining
    0.65
    thed
    0.65
    Activations Density 0.638%

    No Known Activations