© 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. 240919
    Prev
    Next
    INDEX
    Explanations

    increment and decrement operators

    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
     クリスマス
    0.54
     क्रिसमस
    0.51
    क्राइब
    0.50
    クリスマス
    0.49
    立刻
    0.49
    سك
    0.44
     studente
    0.44
    侄
    0.44
    几天
    0.44
     argentino
    0.43
    POSITIVE LOGITS
     eux
    0.43
     applied
    0.42
     ση
    0.41
    postos
    0.40
     اع
    0.40
     sequential
    0.39
     змін
    0.39
     executed
    0.38
    ställ
    0.38
    zé
    0.38
    Activations Density 0.002%

    No Known Activations