© 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. 41-GEMMASCOPE-2-RES-262K
    7. 62219
    Prev
    Next
    INDEX
    Explanations

    Foreign, speaking, named, starts, backward, takes

    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_all/layer_41_width_262k_l0_big
    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
    BigAutoField
    0.38
    icrosoft
    0.35
     deviceInfo
    0.35
    ়া
    0.34
     सहन
    0.34
    PLC
    0.34
    明
    0.33
     lashed
    0.33
     plc
    0.33
     atrop
    0.33
    POSITIVE LOGITS
     चार्
    0.41
    CharArray
    0.40
     Cornwall
    0.38
     ശക്ത
    0.38
    charger
    0.38
     말
    0.37
    PERS
    0.37
    Twenty
    0.36
     une
    0.36
     Metric
    0.36
    Activations Density 0.071%

    No Known Activations