© 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. 7967
    Prev
    Next
    INDEX
    Explanations

    mean squared or absolute

    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
     mL
    0.91
     slats
    0.87
     ml
    0.86
    梧
    0.86
    ml
    0.84
    mL
    0.83
    indle
    0.82
    患者
    0.78
     ч
    0.77
     gums
    0.76
    POSITIVE LOGITS
    ZER
    0.97
    dex
    0.97
     Moshe
    0.92
    Avi
    0.91
     Bik
    0.91
    셩
    0.90
    Jenn
    0.90
     تشدد
    0.90
    Aly
    0.90
    бер
    0.90
    Activations Density 0.038%

    No Known Activations