© 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. 71204
    Prev
    Next
    INDEX
    Explanations

    consideration trip, after being, output overload, she anticipates

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

    spacious comfort, Technical Support, you know

    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
    0.50
    k
    0.46
    B
    0.46
    стры
    0.45
    Smart
    0.43
    ifty
    0.42
    이
    0.42
     своим
    0.42
    “
    0.42
    Rice
    0.41
    POSITIVE LOGITS
     Untersuchung
    0.47
    ရောက်
    0.46
    ങ്ങളിൽ
    0.46
     Auswirkungen
    0.46
     Auschwitz
    0.45
     unabhängig
    0.45
     شہادت
    0.45
     പാറ
    0.44
     접근
    0.44
     descubrimiento
    0.43
    Activations Density 0.001%

    No Known Activations