© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11433
    Prev
    Next
    INDEX
    Explanations

    the act of watching

    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_13_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
    
    2.44
     typesetting
    2.28
    ecirc
    2.23
    “”
    2.23
    |}
    2.21
    Github
    2.20
    necked
    2.20
    Monthly
    2.13
     له‌
    2.10
    িনিয়র
    2.08
    POSITIVE LOGITS
    ل
    2.19
    orn
    2.04
    嗒
    2.03
    SizeMode
    2.03
    ்
    2.02
    rella
    2.02
    ung
    2.01
    sports
    1.94
    ungnya
    1.94
    mitting
    1.93
    Activations Density 0.074%

    No Known Activations