© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 197355
    Prev
    Next
    INDEX
    Explanations

    location and usage

    np_acts-logits-general · gemini-2.5-flash-lite

    Cabinet Widths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     Occasionally
    0.48
    ISTAN
    0.48
    いつも
    0.47
     Furthermore
    0.46
     Often
    0.46
    ม
    0.46
    accommodation
    0.44
    in
    0.44
     This
    0.44
    R
    0.44
    POSITIVE LOGITS
     usada
    0.55
     chọn
    0.54
     gründ
    0.54
     medizin
    0.52
     mostrar
    0.51
     függvény
    0.51
     atualizar
    0.51
    лд
    0.50
     strán
    0.50
     mostrou
    0.50
    Activations Density 0.000%

    No Known Activations