© 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. 125575
    Prev
    Next
    INDEX
    Explanations

    stopping words or abbreviations

    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
     зараз
    0.51
    悆
    0.47
    নৈতিক
    0.47
     Franchise
    0.44
     Shareholders
    0.44
     букме
    0.44
     দফা
    0.43
     плате
    0.43
     DISPLAYS
    0.43
    ᆯ
    0.42
    POSITIVE LOGITS
     achet
    0.52
     nous
    0.48
     nomm
    0.45
    elling
    0.45
     abbreviations
    0.45
     connotations
    0.43
     exper
    0.42
     well
    0.42
    kee
    0.42
     measurements
    0.42
    Activations Density 0.011%

    No Known Activations