© 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. 5310
    Prev
    Next
    INDEX
    Explanations

    wa or essay

    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
    ي
    1.01
    Possibly
    0.75
    Percentages
    0.75
    IE
    0.74
    ुष
    0.74
    lobin
    0.73
     Вики
    0.72
    rate
    0.71
    ciata
    0.71
    accro
    0.71
    POSITIVE LOGITS
     enkelt
    0.88
    новый
    0.80
     evangel
    0.77
     hopeful
    0.72
    よい
    0.71
    ?
    0.70
     heft
    0.70
     hope
    0.69
    頑張
    0.68
     viejo
    0.68
    Activations Density 0.001%

    No Known Activations