© 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. 189022
    Prev
    Next
    INDEX
    Explanations

    description or observation

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

    script!

    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
    tobs
    0.48
    ویه
    0.48
    ਗ
    0.48
    ্যন্তরীণ
    0.48
    بيه
    0.48
    ס
    0.47
     ساری
    0.47
    娱乐
    0.47
    农业
    0.47
    য
    0.46
    POSITIVE LOGITS
    0.54
     ^
    0.54
     [
    0.51
     見
    0.51
     Scha
    0.50
     Commission
    0.49
     See
    0.48
     Seeing
    0.48
     Fa
    0.48
     an
    0.47
    Activations Density 0.001%

    No Known Activations