© 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. 229658
    Prev
    Next
    INDEX
    Explanations

    two volumes

    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
     апо
    0.50
     инстру
    0.50
    шение
    0.49
     nicknamed
    0.49
    Ћ
    0.49
    driver
    0.49
     effekt
    0.49
    вно
    0.49
    ط
    0.48
    ט
    0.48
    POSITIVE LOGITS
     Detecting
    0.47
     हिस्सा
    0.45
     Pedagog
    0.44
     শেষ
    0.43
     Boul
    0.42
     Cosm
    0.41
     Boon
    0.41
     Gandh
    0.40
    lawful
    0.40
     Nghi
    0.40
    Activations Density 0.001%

    No Known Activations