© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139852
    Prev
    Next
    INDEX
    Explanations

    poems set

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

    explaining possibilities and causes

    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
    Negative Logits
     Алексей
    0.51
    jokes
    0.50
    வ்வ
    0.47
    ᓚ
    0.47
    好き
    0.46
    рованная
    0.46
     днем
    0.46
     Бүген
    0.46
    Akh
    0.45
    mites
    0.45
    POSITIVE LOGITS
    酥
    0.49
     practice
    0.48
     Rehab
    0.47
     rehabilitate
    0.47
     assure
    0.46
    练习
    0.46
    ứ
    0.46
    场
    0.46
    ĩ
    0.46
     Probate
    0.45
    Activations Density 0.000%

    No Known Activations