© 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. 108190
    Prev
    Next
    INDEX
    Explanations

    specific noun phrases

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

    foreign words and sex

    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
    }_
    0.55
    LEncoder
    0.49
    ست
    0.48
     ripples
    0.48
    Adresse
    0.46
     villains
    0.45
    Customer
    0.45
     examinations
    0.44
    EnumValue
    0.44
     umbrellas
    0.44
    POSITIVE LOGITS
     सेक्स
    0.59
    ñ
    0.53
     Télé
    0.51
    ți
    0.50
    ol
    0.50
     लीवर
    0.48
    il
    0.48
    ños
    0.47
     Wire
    0.47
    og
    0.47
    Activations Density 0.004%

    No Known Activations