© 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. 135653
    Prev
    Next
    INDEX
    Explanations

    christ, CEO, finals, ix

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

    love, parents, dates, statistics

    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
    Ř
    0.43
    Urls
    0.42
    墅
    0.41
    alba
    0.41
    ｉ
    0.41
     সেতু
    0.40
     壁
    0.40
    rios
    0.40
     Url
    0.39
     Gates
    0.39
    POSITIVE LOGITS
    писы
    0.53
     déprimées
    0.49
     ماشینونه
    0.49
     سپورت
    0.48
    🤶
    0.46
     შემთ
    0.45
     infert
    0.45
     поми
    0.45
    ക്കുറ
    0.45
     statistique
    0.45
    Activations Density 0.001%

    No Known Activations