© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10542
    Prev
    Next
    INDEX
    Explanations

    his eyes

    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
    場合があります
    0.94
     التف
    0.91
    itty
    0.85
    Ti
    0.83
    ogen
    0.82
    internal
    0.81
    lyde
    0.81
    웁
    0.81
    밋
    0.80
    magn
    0.80
    POSITIVE LOGITS
     bari
    1.04
    鸫
    1.01
     처음
    1.00
     stopni
    0.97
    બસ
    0.96
     MOTOR
    0.95
     JOUR
    0.94
     ничек
    0.94
     HOL
    0.93
    ль
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.