© 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. 166659
    Prev
    Next
    INDEX
    Explanations

    specific phrases and locations

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

    purpose, frequency, monitoring, light, release

    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
    Instantiation
    0.48
    exponent
    0.43
    인
    0.41
    x
    0.41
     \{
    0.40
    behav
    0.40
    s
    0.40
     ዳ
    0.39
     regime
    0.39
    gauge
    0.39
    POSITIVE LOGITS
     Islington
    0.50
     adequada
    0.49
    褂
    0.48
    ைத்
    0.47
    قد
    0.46
    iiv
    0.46
     gibt
    0.45
    щими
    0.45
    大きく
    0.45
     Acoust
    0.45
    Activations Density 0.000%

    No Known Activations