© 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. 129818
    Prev
    Next
    INDEX
    Explanations

    domain-specific phrases

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

    inventive, biking, from

    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
    ᴴ
    0.50
     Alltag
    0.46
     horrifying
    0.46
     prequel
    0.46
     badass
    0.45
    ḧ
    0.45
     brutal
    0.44
     Eternal
    0.43
     Korean
    0.43
     २०२२
    0.43
    POSITIVE LOGITS
    coord
    0.49
    applicants
    0.42
    AREA
    0.42
    段階
    0.42
    FIGURE
    0.41
    $:
    0.40
    一種
    0.40
    Figure
    0.39
     ايجاد
    0.39
    COCH
    0.39
    Activations Density 0.001%

    No Known Activations