© 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. 103764
    Prev
    Next
    INDEX
    Explanations

    foreign countries and personal items

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

    sensitive topics and their risks

    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
    use
    0.55
    of
    0.53
    ree
    0.53
    ir
    0.50
    ok
    0.50
    Re
    0.50
    Bar
    0.49
    u
    0.49
    am
    0.47
    up
    0.46
    POSITIVE LOGITS
     diri
    0.63
     trasm
    0.59
     primeira
    0.55
     contenido
    0.50
     lira
    0.50
     araştırm
    0.50
     HUNT
    0.50
     luta
    0.49
    ાન
    0.48
     conteudo
    0.48
    Activations Density 0.000%

    No Known Activations