© 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. 192550
    Prev
    Next
    INDEX
    Explanations

    actions following events

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

    removing agency or consent

    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
     person
    0.45
     parka
    0.43
     eigens
    0.42
    损坏
    0.42
     Decedent
    0.42
     kolor
    0.41
     Map
    0.41
     incrível
    0.41
    饰
    0.41
     myster
    0.40
    POSITIVE LOGITS
     સ્વા
    0.49
     তারাও
    0.49
     बच्च
    0.46
     बैठक
    0.42
    software
    0.41
    小学生
    0.41
     সর্বত্র
    0.41
    ACE
    0.40
    lığını
    0.40
    haw
    0.40
    Activations Density 0.001%

    No Known Activations