© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10457
    Prev
    Next
    INDEX
    Explanations

    tokenization process

    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
    란
    1.82
     начина
    1.78
     интере
    1.74
    дные
    1.73
    אנ
    1.70
     ومش
    1.70
    Blow
    1.67
     собой
    1.67
    ！」
    1.65
    ！）
    1.62
    POSITIVE LOGITS
    isiert
    1.86
    Fast
    1.79
    voerd
    1.79
    ə
    1.78
     ventricular
    1.75
     diluted
    1.75
     glu
    1.74
     Fast
    1.73
     genom
    1.73
     uterine
    1.72
    Activations Density 0.143%

    No Known Activations