© 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. 216094
    Prev
    Next
    INDEX
    Explanations

    rear floor mats, Lion King Coloring, tiny toilets, llvm::

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

    affirmative action, reliance, colorblind

    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
    orit
    0.45
     Hanya
    0.42
    टेगरी
    0.42
    ორცი
    0.40
    時に
    0.40
    andam
    0.40
    で行
    0.40
    циям
    0.40
     विधि
    0.39
    谷
    0.39
    POSITIVE LOGITS
     perdió
    0.46
     തെ
    0.42
     সক্র
    0.42
     satan
    0.41
     sind
    0.41
     הראשון
    0.41
     satire
    0.40
    🆚
    0.40
     Satan
    0.40
     അതിന്റെ
    0.40
    Activations Density 0.000%

    No Known Activations