© 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. 180040
    Prev
    Next
    INDEX
    Explanations

    enable to perform services

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

    list structures and descriptions

    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
     thì
    0.47
     behov
    0.46
     handleDelete
    0.46
    ↵
    0.42
     رفت
    0.42
     তখন
    0.42
    зора
    0.42
     Fleur
    0.40
     hologram
    0.40
     reflexes
    0.39
    POSITIVE LOGITS
    ɚ
    0.50
    avorable
    0.49
     خدنا
    0.49
    溶解
    0.47
     জড়িয়ে
    0.46
    roep
    0.45
    olisme
    0.45
     ধন্যবাদ
    0.45
     পেয়েছিলাম
    0.44
    数字
    0.44
    Activations Density 0.000%

    No Known Activations