© 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. 205319
    Prev
    Next
    INDEX
    Explanations

    foreign words and city names

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

    "follow instructions" and "value"

    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
    Holder
    0.43
     responsiveness
    0.42
    λώ
    0.42
     welcomed
    0.42
    rapport
    0.42
    ита
    0.41
    Rachel
    0.41
    '@
    0.41
    Tucker
    0.40
    let
    0.40
    POSITIVE LOGITS
     Anambra
    0.50
    ।,
    0.49
    ใหม่
    0.48
     nieuwe
    0.48
     २०२
    0.48
     neue
    0.47
     Angleterre
    0.47
     przez
    0.47
     Kyushu
    0.47
     kuy
    0.47
    Activations Density 0.001%

    No Known Activations