© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2859
    Prev
    Next
    INDEX
    Explanations

    il medico

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     технологии
    1.80
     RouterModule
    1.78
     tecnologías
    1.77
    URLConnection
    1.76
    )').
    1.71
    設施
    1.70
    紗
    1.63
    歷史
    1.61
    玩
    1.57
    ́ng
    1.56
    POSITIVE LOGITS
     proie
    1.57
     pani
    1.54
     confisc
    1.54
    empty
    1.50
    eru
    1.49
     damped
    1.48
    Wert
    1.48
    £
    1.45
    beige
    1.43
    clipped
    1.41
    Activations Density 0.000%

    No Known Activations