© 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. 17534
    Prev
    Next
    INDEX
    Explanations

    note:

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

    dates and details

    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
    ี้
    0.62
    antaranya
    0.58
    ਾਰ
    0.58
    .'),
    0.57
    ן
    0.53
    人
    0.52
    נה
    0.51
    ่น
    0.51
    Renk
    0.51
    UILLER
    0.50
    POSITIVE LOGITS
     The
    0.94
     I
    0.88
     A
    0.79
     ALL
    0.73
     L
    0.71
     THE
    0.70
     S
    0.69
     G
    0.67
     Our
    0.66
     K
    0.66
    Activations Density 0.118%

    No Known Activations