© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7872
    Prev
    Next
    INDEX
    Explanations

    code structures and foreign words

    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_22_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
     Nek
    1.13
    renees
    1.07
     内
    1.01
     اعمل
    0.96
    cki
    0.94
     Refuge
    0.93
    小平
    0.92
    ूण
    0.91
     Vern
    0.91
     входя
    0.90
    POSITIVE LOGITS
    age
    1.01
    await
    0.89
    ੍
    0.85
    ^{*}
    0.84
    ajati
    0.82
     conjunta
    0.81
     await
    0.81
    汎
    0.80
    áž
    0.80
     intelekt
    0.79
    Activations Density 0.000%

    No Known Activations