© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 95629
    Prev
    Next
    INDEX
    Explanations

    car models, likelihood, persons, public/private sectors, personal items

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

    reentrancy calls

    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
     культуры
    0.48
     বাঙ্গাল
    0.46
     STEELS
    0.46
     ভাষা
    0.46
     فرهنگی
    0.46
     языка
    0.45
     భాష
    0.45
    鐩
    0.44
    语言
    0.44
     文化
    0.44
    POSITIVE LOGITS
     seiner
    0.57
     sigmoid
    0.48
     mutta
    0.47
     a
    0.47
     mercenary
    0.45
     Enfer
    0.44
     gynec
    0.43
     import
    0.42
     Fannie
    0.42
     optimum
    0.41
    Activations Density 0.000%

    No Known Activations