© 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. 119946
    Prev
    Next
    INDEX
    Explanations

    dates, operations, series, home, notify

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

    programming libraries and concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    さえ
    0.51
    짱
    0.45
     folders
    0.45
    千萬
    0.45
    꼰
    0.44
     MALL
    0.44
     двох
    0.43
    𝘷
    0.43
     cálculos
    0.42
    zigzag
    0.41
    POSITIVE LOGITS
     Flowering
    0.42
     dysph
    0.42
     maintained
    0.41
    ulatory
    0.41
     Dairy
    0.39
     घाटी
    0.39
    த்திலேயே
    0.39
     Rhine
    0.39
     maintains
    0.39
     βρί
    0.39
    Activations Density 0.001%

    No Known Activations