© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4431
    Prev
    Next
    INDEX
    Explanations

    Compile Time

    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
    Muito
    0.76
    Tiempo
    0.75
    Você
    0.75
    مز
    0.73
    ર્
    0.73
    اکي
    0.72
    ياً
    0.71
    u
    0.71
    ణ
    0.71
    粵
    0.71
    POSITIVE LOGITS
     godziny
    0.71
    toilet
    0.71
     Оте
    0.70
     нару
    0.69
    eine
    0.68
     diocese
    0.68
    thoughtId
    0.68
     буты
    0.68
    फारिश
    0.68
    temperatur
    0.67
    Activations Density 0.001%

    No Known Activations