© 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. 193322
    Prev
    Next
    INDEX
    Explanations

    people with

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

    racial language

    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
    沒
    0.50
    滿
    0.49
    做
    0.46
    莊
    0.46
    вої
    0.44
     зробити
    0.44
    満
    0.44
     tehdä
    0.44
    超
    0.43
     pleno
    0.43
    POSITIVE LOGITS
     skipper
    0.47
     driveway
    0.46
     Verkehrs
    0.46
     expatri
    0.45
     immigrants
    0.44
     dissimilar
    0.44
     Indians
    0.42
    uruan
    0.42
     تردد
    0.41
    atthakath
    0.41
    Activations Density 0.001%

    No Known Activations