© 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. 21405
    Prev
    Next
    INDEX
    Explanations

    once again

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

    Once you

    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
    QUESTION
    0.66
     uso
    0.61
    はどう
    0.61
    BEFORE
    0.60
     trước
    0.59
    IMPORTANT
    0.59
     considerar
    0.59
    す
    0.58
    ጲ
    0.57
     kısm
    0.56
    POSITIVE LOGITS
     Once
    0.89
     einmal
    0.78
     once
    0.72
    Once
    0.70
    一旦
    0.67
    يه
    0.61
     You
    0.60
    ête
    0.57
    etlen
    0.57
     एकदा
    0.57
    Activations Density 0.065%

    No Known Activations