© 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. 116198
    Prev
    Next
    INDEX
    Explanations

    history of, how well, type race, student achievement

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

    how easy it is

    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
     ersten
    0.45
     emulate
    0.45
     peroneal
    0.45
     situate
    0.45
    راً
    0.45
     dilemmas
    0.43
     rome
    0.43
    ⦖
    0.43
     مقارنه
    0.42
     وتب
    0.42
    POSITIVE LOGITS
    ä
    0.55
    ө
    0.50
     Tính
    0.49
    a
    0.48
    명
    0.47
     Hồ
    0.46
     Enseñanza
    0.45
    ла
    0.45
     Flüss
    0.44
     Leistungs
    0.44
    Activations Density 0.000%

    No Known Activations