© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14553
    Prev
    Next
    INDEX
    Explanations

    python imports

    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_24_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
    У
    0.98
    Чита
    0.89
    IVING
    0.89
    І
    0.89
     aport
    0.89
    Agricult
    0.88
    之上
    0.86
    Fuente
    0.84
    룹
    0.84
    出
    0.84
    POSITIVE LOGITS
    т
    1.07
    ت
    0.94
    سازی
    0.82
    totals
    0.80
    тную
    0.80
    ceğim
    0.79
    𝐧
    0.78
    𝐭
    0.78
    𝘮
    0.77
    ूँगा
    0.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.