© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4516
    Prev
    Next
    INDEX
    Explanations

    foreign languages and numerals

    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
     Di
    2.09
     Method
    2.07
     V
    2.04
     One
    1.99
     S
    1.96
     Re
    1.93
     Word
    1.93
     Out
    1.91
     Ch
    1.90
     P
    1.88
    POSITIVE LOGITS
     кван
    3.92
     скульп
    3.83
     излу
    3.74
    ните
    3.61
    rinsic
    3.61
    ٦
    3.60
    ٨
    3.57
     инфра
    3.57
    ٧
    3.57
    łaś
    3.56
    Activations Density 0.091%

    No Known Activations