© 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. 222818
    Prev
    Next
    INDEX
    Explanations

    numbers and phone numbers

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

    dry things

    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
    ;*/
    0.48
     Vamp
    0.45
     출시
    0.45
     እስከ
    0.44
     বয়সে
    0.43
     Amsterdam
    0.43
    ,{
    0.43
     নব
    0.43
     destacados
    0.43
    初回
    0.42
    POSITIVE LOGITS
    驯
    0.52
     скорость
    0.50
    厄
    0.50
    护
    0.48
     gonorrhea
    0.46
     قاعدة
    0.45
    皮肤
    0.44
     փ
    0.44
     ط
    0.43
     नोटिफिकेशन
    0.43
    Activations Density 0.004%

    No Known Activations