© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92630
    Prev
    Next
    INDEX
    Explanations

    closest belt spark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    бу
    0.51
    ллин
    0.49
    яти
    0.46
    эн
    0.46
    кри
    0.45
    Immediately
    0.45
    哽
    0.45
    ницу
    0.44
    лое
    0.44
    рите
    0.43
    POSITIVE LOGITS
     employees
    0.46
     travailleurs
    0.46
     EVs
    0.45
     Sér
    0.45
     électriques
    0.45
     pracowników
    0.43
     ‘
    0.43
     Č
    0.43
     oscilloscope
    0.42
     ong
    0.42
    Activations Density 0.003%

    No Known Activations