© 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. 87143
    Prev
    Next
    INDEX
    Explanations

    kept abreast, problem solving

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

    masked words

    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
     -(
    0.55
    gis
    0.49
    coats
    0.48
    downs
    0.46
    s
    0.46
    koj
    0.46
     ل
    0.45
     list
    0.44
    dine
    0.43
     finds
    0.43
    POSITIVE LOGITS
     vittime
    0.52
    蹩
    0.50
     victime
    0.49
    вшись
    0.49
    続けて
    0.49
     좋아하는
    0.49
     Milliarden
    0.49
    ಡಿದ
    0.47
    ต่อเนื่อง
    0.47
    嘆
    0.47
    Activations Density 0.001%

    No Known Activations