© 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. 180215
    Prev
    Next
    INDEX
    Explanations

    types of firms managed

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

    how "good"

    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
    мя
    0.55
    ை
    0.46
    غال
    0.45
    ද්ග
    0.45
    にも
    0.44
    oughed
    0.44
     رشد
    0.43
    ח
    0.43
    мые
    0.42
    ول
    0.42
    POSITIVE LOGITS
     Liberties
    0.48
    took
    0.48
     Assemblies
    0.45
    trainer
    0.44
    analytical
    0.43
    veri
    0.43
    裁判
    0.43
    unitary
    0.43
    reach
    0.42
     अंजाम
    0.42
    Activations Density 0.001%

    No Known Activations