© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13490
    Prev
    Next
    INDEX
    Explanations

    trading, React, movements

    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_31_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
    alle
    0.55
    …’
    0.54
    찝
    0.51
    searching
    0.50
    찧
    0.50
     vijf
    0.49
    ape
    0.48
     cuidad
    0.48
    anh
    0.48
    zocht
    0.48
    POSITIVE LOGITS
     reveals
    0.60
    揭
    0.58
     सना
    0.57
    ليس
    0.57
     perforated
    0.57
     Пор
    0.56
    罄
    0.56
    ﺢ
    0.56
     Akufo
    0.55
     dikatakan
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.