© 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. 62106
    Prev
    Next
    INDEX
    Explanations

    made in or made with

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

    objective / zigzagging

    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
     diamètre
    0.50
     (\
    0.48
    (\
    0.47
     neuf
    0.46
    _{\
    0.46
     (>
    0.45
     ($\
    0.45
     [(
    0.44
     epithelium
    0.44
     preferentially
    0.44
    POSITIVE LOGITS
     डेब्यू
    0.54
     პირადი
    0.51
     አንድ
    0.50
     kurta
    0.50
    事が
    0.49
    वरिश
    0.48
    瑣
    0.48
    枤
    0.47
     דבר
    0.46
     ან
    0.46
    Activations Density 0.000%

    No Known Activations