© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218446
    Prev
    Next
    INDEX
    Explanations

    direct impact

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

    employee discrimination bank

    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
     secund
    0.50
    жень
    0.49
    ujući
    0.47
    脩
    0.45
     próprias
    0.45
     espacial
    0.44
    ικη
    0.44
     costos
    0.44
     л
    0.44
     própria
    0.44
    POSITIVE LOGITS
     yard
    0.47
     antics
    0.47
     -----------
    0.44
     PCI
    0.43
     Ankara
    0.43
    urts
    0.43
    faced
    0.43
     hostel
    0.43
     sell
    0.42
     অন্যদিকে
    0.41
    Activations Density 0.000%

    No Known Activations