© 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. 205954
    Prev
    Next
    INDEX
    Explanations

    national or legal entities

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

    legal and governmental entities

    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
    o
    0.56
    xr
    0.49
    ifting
    0.47
    e
    0.46
     recorder
    0.46
    primary
    0.46
    cd
    0.46
    ocardi
    0.44
    p
    0.44
    a
    0.44
    POSITIVE LOGITS
    国の
    0.53
    国的
    0.47
     povos
    0.46
     unlawfully
    0.45
     naciones
    0.45
     lawfully
    0.45
     ACLU
    0.44
     ملت
    0.44
     держави
    0.44
    تما
    0.44
    Activations Density 0.001%

    No Known Activations