© 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. 63173
    Prev
    Next
    INDEX
    Explanations

    skilled craftsman, great firmness

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

    strikes and demonstrations

    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
     AppPage
    0.45
     tcpHeader
    0.45
    Academy
    0.44
     کمپنی
    0.44
     சொந்த
    0.44
     garantire
    0.43
     Museo
    0.42
    ICKEL
    0.42
    䒷
    0.42
    రిగ
    0.41
    POSITIVE LOGITS
     occupants
    0.45
     because
    0.45
     sufferers
    0.43
    lul
    0.43
    t
    0.43
    ut
    0.43
    st
    0.43
     internation
    0.43
    ֆ
    0.42
     urbanization
    0.42
    Activations Density 0.000%

    No Known Activations