© 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. 16-GEMMASCOPE-2-RES-262K
    4. 30631
    Prev
    Next
    INDEX
    Explanations

    long, cuz, etc

    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_16_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
    с
    0.50
    на
    0.50
     reduced
    0.49
     carriage
    0.48
     business
    0.46
     conditioned
    0.45
     manic
    0.44
     provenance
    0.44
     quotidien
    0.43
     constrained
    0.43
    POSITIVE LOGITS
    bles
    0.57
    كر
    0.56
    كي
    0.52
    ábamos
    0.51
     ক্যান্স
    0.51
    喡
    0.51
     Ebola
    0.50
    㺪
    0.49
    ⨔
    0.49
    bek
    0.48
    Activations Density 0.000%

    No Known Activations