© 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. 3798
    Prev
    Next
    INDEX
    Explanations

    integration and connectivity

    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
    ेक्ट
    1.31
    eni
    1.19
    してる
    1.09
    enes
    1.09
    Veg
    1.07
    fern
    1.07
    哋
    1.06
    advice
    1.06
    παϊ
    1.06
     opl
    1.06
    POSITIVE LOGITS
    入住
    2.36
     ห้อง
    1.90
    벨
    1.90
     inicio
    1.86
    dsale
    1.80
    起床
    1.80
     ومع
    1.79
     Arrival
    1.78
     Entered
    1.75
     бонусу
    1.72
    Activations Density 0.334%

    No Known Activations