© 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. 5252
    Prev
    Next
    INDEX
    Explanations

    modern features & technologies

    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
    ﻟ
    0.95
    ا
    0.93
    кс
    0.88
    ่
    0.82
    нде
    0.80
    ت
    0.80
    ль
    0.79
    ла
    0.77
    տ
    0.77
    нг
    0.75
    POSITIVE LOGITS
     adegu
    0.84
     gegenüber
    0.83
     খালে
    0.80
     eben
    0.79
     deberá
    0.78
    ත්වය
    0.78
     adalah
    0.77
     तरीका
    0.77
    化的
    0.77
     stellt
    0.77
    Activations Density 0.018%

    No Known Activations