© 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. 212643
    Prev
    Next
    INDEX
    Explanations

    acquisition/gap between

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

    foreign language characters

    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
     і
    0.48
    家中
    0.42
    音乐
    0.41
    naio
    0.41
     a
    0.40
     competitively
    0.40
    大法
    0.40
     и
    0.40
    мпа
    0.40
    更加
    0.40
    POSITIVE LOGITS
     terus
    0.54
    ر
    0.53
     transfert
    0.51
     kaldır
    0.49
     jarak
    0.47
     मिळाली
    0.47
    উঠ
    0.47
     mempertahankan
    0.47
    ロン
    0.46
    anfaatkan
    0.45
    Activations Density 0.001%

    No Known Activations