© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84591
    Prev
    Next
    INDEX
    Explanations

    know where

    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
     unid
    0.48
     delectable
    0.47
     sets
    0.46
     provisioning
    0.46
    н
    0.45
    in
    0.45
     набор
    0.44
     mesta
    0.44
     apoi
    0.43
     parametric
    0.42
    POSITIVE LOGITS
    SystemCall
    0.55
    SubDirectory
    0.49
    ရှင်
    0.46
    ह्न
    0.44
    Completion
    0.43
    发送
    0.43
    aporan
    0.43
    सेवी
    0.43
    导致
    0.42
    噉
    0.42
    Activations Density 0.003%

    No Known Activations