© 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. 3588
    Prev
    Next
    INDEX
    Explanations

    summarize

    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
    чески
    2.15
    巉
    2.10
    elik
    2.08
    izacja
    2.05
    cian
    2.01
    fitted
    1.99
    zten
    1.96
     Testing
    1.95
    boden
    1.92
     gewe
    1.90
    POSITIVE LOGITS
    !("{}",
    2.94
    webtoken
    2.64
     '\\;'
    2.50
     MACHINE
    2.45
    dbo
    2.43
     fadeInUp
    2.41
     conteudo
    2.39
    实话
    2.32
    бами
    2.31
    ্যা
    2.31
    Activations Density 0.044%

    No Known Activations