© 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. 213291
    Prev
    Next
    INDEX
    Explanations

    I

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

    satisfaction scores related to

    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
    പു
    0.54
    ની
    0.53
    அ
    0.53
    ן
    0.52
    ân
    0.49
     Bajaj
    0.49
     crowning
    0.47
    ımızı
    0.47
    ুপ্ত
    0.47
     désormais
    0.47
    POSITIVE LOGITS
    >
    0.45
    mfenced
    0.44
    create
    0.44
    option
    0.42
    stable
    0.42
    ype
    0.41
    querySelector
    0.41
     x
    0.41
    lat
    0.41
    ceil
    0.41
    Activations Density 0.000%

    No Known Activations