© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 44213
    Prev
    Next
    INDEX
    Explanations

    poison, Mozilla, League, det, Solver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ה
    0.73
    의
    0.65
    Р
    0.63
     cognizant
    0.60
    એ
    0.60
    ın
    0.60
     nascent
    0.59
     лиде
    0.59
     legate
    0.58
    지
    0.58
    POSITIVE LOGITS
    ä
    0.69
    é
    0.62
    ż
    0.61
    h
    0.59
    qu
    0.57
    ama
    0.57
    وم
    0.56
    ver
    0.56
    og
    0.55
     Cine
    0.55
    Activations Density 0.001%

    No Known Activations