© 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. 12457
    Prev
    Next
    INDEX
    Explanations

    comeback specific contexts

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

    lockdown and coronavirus

    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
     ২০১২
    0.55
     ২০১১
    0.50
     xrange
    0.49
     २०१
    0.48
    Universität
    0.45
     спект
    0.43
    BeforeText
    0.43
    ೫
    0.43
    ಬ್ಬಿಣ
    0.42
     finition
    0.42
    POSITIVE LOGITS
     코로나
    1.91
     COVID
    1.89
     Covid
    1.82
     coronavirus
    1.78
    COVID
    1.75
     Coronavirus
    1.73
     covid
    1.69
    coronavirus
    1.68
     कोरोना
    1.66
     लॉकडाउन
    1.65
    Activations Density 0.036%

    No Known Activations