© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1815
    Prev
    Next
    INDEX
    Explanations

    ; treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     Vee
    2.02
    ungannya
    1.97
    فير
    1.95
    hoea
    1.95
     速
    1.92
    Re
    1.90
    dates
    1.87
     schemes
    1.86
     Dates
    1.85
    ｖ
    1.85
    POSITIVE LOGITS
    rinsic
    3.23
    ຖານ
    3.07
    ທີ່ຈະ
    2.85
    7
    2.75
     dezvolt
    2.72
    avic
    2.64
    ที่จะ
    2.63
    8
    2.60
     để
    2.60
     untuk
    2.58
    Activations Density 1.037%

    No Known Activations