© 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. 218085
    Prev
    Next
    INDEX
    Explanations

    how much is

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

    specific topics and questions

    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
     Interactions
    0.50
     focusing
    0.49
     interactions
    0.49
     huddled
    0.45
     finalizing
    0.45
     irrevers
    0.44
     Focusing
    0.44
     irreversible
    0.43
    幷
    0.43
    私たちは
    0.42
    POSITIVE LOGITS
    程
    0.49
     દર
    0.48
    olov
    0.47
    fot
    0.46
     oğ
    0.46
     तहे
    0.46
     mencionados
    0.45
    f
    0.45
     चौक
    0.45
    CEST
    0.44
    Activations Density 0.000%

    No Known Activations