© 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. 146683
    Prev
    Next
    INDEX
    Explanations

    unborn fetus, gallon recovery

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

    defining principles or rules

    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
     εἰ
    0.53
    暊
    0.48
     inwoners
    0.48
    જી
    0.47
    平时
    0.47
    iril
    0.47
    弛
    0.45
     प्रीवियस
    0.44
     ক
    0.43
     заявления
    0.43
    POSITIVE LOGITS
    the
    0.57
    Domain
    0.51
    anna
    0.50
    front
    0.50
    Center
    0.50
    Hub
    0.49
    that
    0.49
    S
    0.49
    Haw
    0.48
    .
    0.48
    Activations Density 0.000%

    No Known Activations