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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 44163
    Prev
    Next
    INDEX
    Explanations

    library imports

    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_262k_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
    াতি
    1.23
    ться
    1.13
    牡丹
    1.13
    গুণ
    1.09
    हारिक
    1.09
    மாக
    1.05
    课
    1.05
    或者是
    1.04
     volley
    1.04
     spät
    1.03
    POSITIVE LOGITS
    p
    1.55
    т
    1.51
    ف
    1.45
    м
    1.39
    ا
    1.30
    ków
    1.30
    t
    1.27
    ال
    1.26
    وا
    1.25
    ot
    1.22
    Activations Density 0.003%

    No Known Activations