© 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. 199634
    Prev
    Next
    INDEX
    Explanations

    selfcreatealter

    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
    По
    0.50
    Се
    0.49
    <0x97>
    0.48
    Не
    0.47
    ş
    0.47
    На
    0.46
    ként
    0.45
    に取り組
    0.45
    Н
    0.45
    ными
    0.44
    POSITIVE LOGITS
     Plateau
    0.56
     surcharge
    0.55
     Phones
    0.53
     Sustain
    0.51
     Economy
    0.50
     Trade
    0.50
     Customers
    0.49
     Addis
    0.48
     Swans
    0.47
     स्वतः
    0.47
    Activations Density 0.002%

    No Known Activations