© 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. 10703
    Prev
    Next
    INDEX
    Explanations

    cricket wickets

    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
    er
    3.74
    <bos>
    3.68
    ার
    3.10
    erar
    3.00
    င်
    2.87
    hain
    2.84
    enang
    2.81
    angana
    2.78
    erode
    2.75
    rinth
    2.74
    POSITIVE LOGITS
    蟀
    2.47
    2.36
    
    2.02
    ,--
    2.01
     Suche
    2.00
    ुस्तान
    1.94
    
    1.94
    ally
    1.94
    ক্তি
    1.91
    ীব্র
    1.90
    Activations Density 0.005%

    No Known Activations