© 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. 22110
    Prev
    Next
    INDEX
    Explanations

    specific nouns and roles

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

    building relationships or learning

    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
     ciência
    0.50
     consentimiento
    0.49
     اہمیت
    0.47
     collaborazione
    0.46
    ч
    0.46
    ulação
    0.45
     Tecnologia
    0.45
     nearby
    0.43
     vicino
    0.43
    āo
    0.43
    POSITIVE LOGITS
     isoforms
    0.43
     поезд
    0.43
    บิน
    0.42
     abbat
    0.42
     उदय
    0.42
     आक्रमण
    0.42
     अटैक
    0.42
     Sailors
    0.42
     ($_
    0.42
    Trait
    0.42
    Activations Density 0.000%

    No Known Activations