© 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. 150941
    Prev
    Next
    INDEX
    Explanations

    my priority

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

    balance, times, Err, each

    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
     声
    0.55
     令
    0.50
     কখনোই
    0.49
     界
    0.48
     विपक्षी
    0.46
     pengaruh
    0.46
     duality
    0.45
     让
    0.45
     造
    0.45
     কখনই
    0.45
    POSITIVE LOGITS
    т
    0.54
    ле
    0.54
    в
    0.53
    plays
    0.46
    ي
    0.46
    You
    0.45
    ت
    0.45
     getters
    0.44
    у
    0.44
    is
    0.44
    Activations Density 0.001%

    No Known Activations