© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 34
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    or
    0.64
    ла
    0.58
    ુ
    0.57
    a
    0.56
    ر
    0.55
    ال
    0.54
    r
    0.52
    ни
    0.52
    𝐚
    0.52
    ли
    0.51
    POSITIVE LOGITS
    をと
    0.41
     unscrupulous
    0.40
     যারা
    0.39
    を有する
    0.37
    要把
    0.36
     reaffirm
    0.36
    要有
    0.36
    睄
    0.36
    を知
    0.36
     تعرض
    0.35
    Activations Density 0.550%

    No Known Activations