© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10987
    Prev
    Next
    INDEX
    Explanations

    let me know if

    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
    cua
    2.33
    رى
    2.32
    مصادر
    2.12
    t
    2.06
     anderer
    2.05
    lardan
    2.02
    heastern
    1.99
     गरजेचे
    1.97
    aia
    1.97
    finden
    1.94
    POSITIVE LOGITS
    К
    2.22
    Б
    2.21
     ק
    2.15
     everyone
    2.09
    ТР
    2.06
     Са
    2.06
     progressed
    2.04
    Пре
    2.03
    ški
    2.01
     よ
    2.00
    Activations Density 0.059%

    No Known Activations