© 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
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15104
    Prev
    Next
    INDEX
    Explanations

    jaw, stone, gravity

    np_acts-logits-general · gemini-2.5-flash-lite

    rephrase statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sizlerle
    0.49
    有了
    0.49
     지난해
    0.49
    allyl
    0.48
     설계
    0.47
    猢
    0.46
    ൦
    0.46
    :"+
    0.46
    akaranam
    0.46
    <unused83>
    0.46
    POSITIVE LOGITS
     vocals
    0.54
     branded
    0.52
     outings
    0.51
     prowess
    0.49
     outing
    0.47
     swo
    0.47
    ’
    0.46
     súa
    0.44
     exceptional
    0.43
     attacks
    0.43
    Activations Density 0.007%

    No Known Activations