© 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. 3580
    Prev
    Next
    INDEX
    Explanations

    journal citation numbers

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

    has about

    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
    निर्माण
    0.56
     enabling
    0.53
    iais
    0.51
    ।*
    0.51
     ascribed
    0.49
    इसलिए
    0.48
    ।
    0.48
    ພວກເຮົາ
    0.47
    indsay
    0.47
    peut
    0.47
    POSITIVE LOGITS
     sinner
    0.46
    jpg
    0.45
     stricken
    0.45
     時
    0.45
     犬
    0.45
     âng
    0.44
     花
    0.43
     länger
    0.43
    REPOSITORY
    0.43
     Kräfte
    0.43
    Activations Density 0.000%

    No Known Activations