© 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. 30113
    Prev
    Next
    INDEX
    Explanations

    simple and easy

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

    dosage/doses

    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
    ט
    0.49
    ۷
    0.47
    ار
    0.46
    ک
    0.45
    но
    0.44
    ات
    0.44
    тун
    0.43
     encontrarás
    0.42
    ہ
    0.42
    ב
    0.41
    POSITIVE LOGITS
     doses
    0.46
     would
    0.44
    dosage
    0.44
     प्रदू
    0.43
    になると
    0.43
     Dosage
    0.43
    izo
    0.42
    iful
    0.41
    would
    0.41
     defies
    0.41
    Activations Density 0.000%

    No Known Activations