© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 242679
    Prev
    Next
    INDEX
    Explanations

    with a proper noun

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ла
    0.54
    an
    0.52
    пи
    0.51
    д
    0.50
    Change
    0.49
    е
    0.47
    ln
    0.47
    ಲ
    0.47
    Button
    0.46
    lin
    0.46
    POSITIVE LOGITS
     rostro
    0.49
     akár
    0.49
     arterial
    0.48
     inspir
    0.48
     antérieur
    0.48
     resounding
    0.48
     pharmacokinetic
    0.48
     dies
    0.47
     tôt
    0.47
    와이스
    0.47
    Activations Density 0.001%

    No Known Activations