© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3864
    Prev
    Next
    INDEX
    Explanations

    concept of loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    ️
    2.19
    ApiException
    2.15
    かれている
    1.99
    おります
    1.92
     empl
    1.90
    oomla
    1.89
     Threatened
    1.85
     Runde
    1.84
    ucumber
    1.84
    lijah
    1.81
    POSITIVE LOGITS
     الوزن
    2.38
    惨
    1.69
    asure
    1.68
    zló
    1.61
    ƙ
    1.60
    ıllı
    1.57
    motivation
    1.56
    Baca
    1.54
    блі
    1.53
    encial
    1.52
    Activations Density 0.116%

    No Known Activations