© 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. 125895
    Prev
    Next
    INDEX
    Explanations

    description of instances or events

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

    listing words like departure, theater, inflammation, conferences, also touch, black pepper

    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
    s
    0.59
    سط
    0.50
    eced
    0.49
    ід
    0.45
    ammonium
    0.45
    ӕ
    0.45
    e
    0.45
    are
    0.45
    は
    0.45
    ä
    0.44
    POSITIVE LOGITS
     స్థాప
    0.52
     teilen
    0.49
     propietario
    0.47
     Beschreibung
    0.46
     moniker
    0.45
     స్టార్
    0.45
     Unternehmen
    0.44
    PhysicalDevice
    0.44
     описание
    0.44
     Bunun
    0.44
    Activations Density 0.000%

    No Known Activations