© 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. 75479
    Prev
    Next
    INDEX
    Explanations

    risks detailed under

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

    crystals formed within

    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
    Not in Any Lists

    No Comments

    Negative Logits
    枟
    0.50
     بٹ
    0.46
     yağ
    0.46
    ếm
    0.44
     beş
    0.43
     журнал
    0.42
     dört
    0.42
     descarga
    0.41
     kullanıcı
    0.41
    chließlich
    0.41
    POSITIVE LOGITS
    👋
    0.45
     introduced
    0.44
    first
    0.43
     Huntsville
    0.43
    瑣
    0.42
     এটাও
    0.42
     materialize
    0.42
    First
    0.41
    Welcome
    0.41
    Premi
    0.41
    Activations Density 0.001%

    No Known Activations