© 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. 12-GEMMASCOPE-2-RES-16K
    7. 9082
    Prev
    Next
    INDEX
    Explanations

    delicate flowers

    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_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
    м
    3.95
    م
    3.86
    म
    2.63
    问题
    2.44
    تان
    2.41
    л
    2.31
    ます
    2.30
    其他
    2.30
    นะ
    2.28
    ről
    2.28
    POSITIVE LOGITS
    f
    2.52
    c
    2.34
     तौर
    2.22
    cage
    2.17
    fibr
    2.17
    ্স
    2.14
     Lithuan
    2.14
    Вы
    2.13
    cation
    2.13
    Всем
    2.09
    Activations Density 0.430%

    No Known Activations