© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 103557
    Prev
    Next
    INDEX
    Explanations

    numbers, brands, or types of events

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

    lists of requirements

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    N
    0.47
     serem
    0.44
    ฺ
    0.44
    itives
    0.43
     centena
    0.42
    ించిన
    0.42
    ump
    0.42
    ᱦ
    0.42
    cohort
    0.41
     मुताबिक
    0.41
    POSITIVE LOGITS
    сності
    0.52
    ঙ্গের
    0.49
    гів
    0.48
     মেসির
    0.47
    ক্স
    0.47
     গোল
    0.46
    লাইট
    0.46
    奖
    0.46
    אל
    0.45
     ማን
    0.44
    Activations Density 0.000%

    No Known Activations