© 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. 170467
    Prev
    Next
    INDEX
    Explanations

    "SHALL" followed by nouns or verbs

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

    control, registry, anesthesia

    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
     mitochond
    0.50
     Mitochond
    0.48
     aort
    0.48
     Vergangenheit
    0.47
     nx
    0.47
    焊
    0.45
    Artifact
    0.45
     chromed
    0.45
     Melinda
    0.44
    关系
    0.44
    POSITIVE LOGITS
    ani
    0.51
    deals
    0.48
    et
    0.46
    va
    0.46
    騾
    0.45
    rane
    0.45
     заключения
    0.44
     заклю
    0.44
    itabbo
    0.43
    rue
    0.43
    Activations Density 0.000%

    No Known Activations