© 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. 85736
    Prev
    Next
    INDEX
    Explanations

    long country sound offering

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

    headline generation

    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
    λ
    0.50
     lambda
    0.49
     intangible
    0.47
     spacing
    0.46
     bush
    0.46
     tile
    0.45
     density
    0.44
     lobes
    0.44
     docks
    0.44
     input
    0.43
    POSITIVE LOGITS
    纖
    0.52
    uisce
    0.50
     هناك
    0.49
     Jehová
    0.48
    这件事
    0.47
    Prote
    0.47
    hala
    0.46
    মুখী
    0.46
    そこで
    0.46
     Protección
    0.46
    Activations Density 0.000%

    No Known Activations