© 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. 75503
    Prev
    Next
    INDEX
    Explanations

    named parent or graduated child

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

    legal context

    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
    سی
    0.50
    कता
    0.46
     remand
    0.46
    راك
    0.45
    BASELINE
    0.44
     tumours
    0.43
     footh
    0.43
    sight
    0.43
    پول
    0.42
    ९
    0.42
    POSITIVE LOGITS
     rojo
    0.51
     হলুদ
    0.50
     amarillo
    0.49
     事件
    0.47
     graduated
    0.43
     Hispanic
    0.42
     বিভক্ত
    0.42
     marrón
    0.41
     appass
    0.41
     eind
    0.41
    Activations Density 0.001%

    No Known Activations