© 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. 53667
    Prev
    Next
    INDEX
    Explanations

    predictable, random, misunderstood, worst, superiority

    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
     nové
    0.47
    ങ്ങള
    0.46
     soziale
    0.46
    <unused1097>
    0.45
    <unused582>
    0.45
    <unused265>
    0.45
    制御
    0.44
    <unused1832>
    0.44
     grü
    0.44
    <unused538>
    0.43
    POSITIVE LOGITS
    ’
    0.54
    in
    0.46
     Online
    0.46
    /
    0.46
     fortnight
    0.45
    endum
    0.45
    #
    0.44
     SPSS
    0.44
    ena
    0.43
     week
    0.43
    Activations Density 0.005%

    No Known Activations