© 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. 246677
    Prev
    Next
    INDEX
    Explanations

    School Shootings

    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
    දා
    0.52
     Ljublj
    0.50
    🥸
    0.48
     یخ
    0.47
    会社の
    0.46
     начина
    0.46
     слов
    0.45
    зидента
    0.45
     ifades
    0.45
     август
    0.45
    POSITIVE LOGITS
    ᆷ
    0.48
     rout
    0.48
    क्टी
    0.47
    ారో
    0.47
    大数据
    0.45
    雦
    0.45
    族
    0.44
    都是
    0.43
    ोगी
    0.43
    overlay
    0.42
    Activations Density 0.000%

    No Known Activations