© 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. 29216
    Prev
    Next
    INDEX
    Explanations

    data and statistics

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

    population counts

    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
     priors
    0.50
     knobs
    0.44
    ﻪ
    0.43
    rimps
    0.42
     Glasses
    0.42
     DEVICES
    0.41
     BUT
    0.40
     knelt
    0.40
     heapq
    0.40
     Modem
    0.40
    POSITIVE LOGITS
     unpredict
    0.51
    ਦ
    0.44
     самой
    0.43
    ensibility
    0.43
     статистики
    0.42
    ต
    0.42
    महाराष्ट
    0.41
     статисти
    0.41
     statistik
    0.41
     статистика
    0.40
    Activations Density 0.000%

    No Known Activations