© 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. 28064
    Prev
    Next
    INDEX
    Explanations

    enters specific areas

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

    learning path; Witwatersrand Gold Rush

    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
    n
    0.62
    șt
    0.53
    ul
    0.48
    ly
    0.47
     gh
    0.46
     Palt
    0.46
    arco
    0.45
    ၀၀
    0.45
     [*
    0.45
    +[
    0.45
    POSITIVE LOGITS
    نو
    0.47
     intrusions
    0.46
     rebates
    0.44
     checkboxes
    0.44
     diagonals
    0.43
     clays
    0.43
    ཊ
    0.43
     numbering
    0.42
    نی
    0.42
     materias
    0.42
    Activations Density 0.000%

    No Known Activations