© 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. 144454
    Prev
    Next
    INDEX
    Explanations

    Python exceptions

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

    AC Motors

    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
     capilla
    0.48
    qui
    0.46
     cont
    0.45
     dene
    0.44
     ព
    0.44
     física
    0.44
     seme
    0.44
     veía
    0.42
     centre
    0.41
     partie
    0.41
    POSITIVE LOGITS
    orsement
    0.54
     hadir
    0.47
    ructose
    0.47
    嗘
    0.46
    specifiedByURL
    0.46
    erjee
    0.43
    обы
    0.43
    𝘞
    0.43
    Attendee
    0.43
     установи
    0.42
    Activations Density 0.002%

    No Known Activations