© 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. 85436
    Prev
    Next
    INDEX
    Explanations

    common phrases or grammatical structures

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

    harm and consequences

    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
    тування
    0.52
    إ
    0.52
    LEGISLATIVE
    0.50
     tumeur
    0.50
     postérieur
    0.50
    وريا
    0.49
    اندا
    0.48
     posl
    0.48
     besuchte
    0.48
    彈
    0.47
    POSITIVE LOGITS
     dispensers
    0.52
     scooters
    0.50
     strollers
    0.50
     trays
    0.49
     toilets
    0.49
     propietarios
    0.49
     artist
    0.49
    dice
    0.47
    ick
    0.47
     overs
    0.47
    Activations Density 0.000%

    No Known Activations