© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10270
    Prev
    Next
    INDEX
    Explanations

    alternative phrasing

    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
     ピアス
    0.66
     Вер
    0.61
     želite
    0.57
     Gü
    0.50
     článku
    0.50
     Núñez
    0.50
    웨
    0.50
    ⁤
    0.50
    র্
    0.48
     福
    0.48
    POSITIVE LOGITS
     FRG
    0.77
    RW
    0.75
     LW
    0.74
     HW
    0.73
     SHF
    0.71
     TK
    0.70
     TM
    0.70
     RB
    0.70
     RW
    0.70
     YT
    0.70
    Activations Density 0.482%

    No Known Activations