© 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. 10712
    Prev
    Next
    INDEX
    Explanations

    watched, then state

    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
    ising
    1.16
    看来
    1.14
    ised
    1.07
    and
    1.07
    ag
    1.02
    we
    1.01
    ac
    1.00
    -
    0.99
    <i>
    0.98
    </i>
    0.96
    POSITIVE LOGITS
     Sản
    2.28
     Đặc
    2.16
     saddas
    2.14
     Màu
    2.13
     জড়ের
    2.12
    >)`](
    2.11
     특징
    2.10
    <bbox>
    2.09
    getBlueTeam
    2.09
     স্থষ্টি
    2.08
    Activations Density 0.261%

    No Known Activations