© 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. 246749
    Prev
    Next
    INDEX
    Explanations

    features, criteria, or types

    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
     ഗ
    0.50
     гі
    0.50
     கல்லூ
    0.49
     ಗ
    0.48
     учитель
    0.48
     க
    0.48
     ж
    0.47
     যৌন
    0.46
     জ
    0.46
     ሴ
    0.46
    POSITIVE LOGITS
    सीना
    0.50
    Variation
    0.47
    Requirement
    0.46
    Contributions
    0.46
    Offer
    0.46
    Item
    0.45
    LIE
    0.43
    Symptoms
    0.43
    ാന
    0.43
    Characteristics
    0.42
    Activations Density 0.000%

    No Known Activations