© 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. 9651
    Prev
    Next
    INDEX
    Explanations

    abbreviations or word endings

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

    abbreviations in technical contexts

    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
    ہ
    0.98
    на
    0.89
    ้
    0.82
    ression
    0.77
     a
    0.77
     you
    0.76
    im
    0.75
    ad
    0.75
     et
    0.74
    uksen
    0.72
    POSITIVE LOGITS
     воздей
    0.82
     rozwiąz
    0.82
     powied
    0.76
    การ
    0.76
     точке
    0.75
     нажа
    0.75
    し
    0.74
    ている
    0.74
     подклю
    0.74
    の色
    0.74
    Activations Density 0.547%

    No Known Activations