© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    teaspoon ingredients

    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
    tı
    1.95
    т
    1.88
    هو
    1.80
    ු
    1.77
    sia
    1.76
    sı
    1.71
    sik
    1.71
    ോ
    1.68
    י
    1.68
    s
    1.68
    POSITIVE LOGITS
     I
    1.35
     bottled
    1.31
     grassroots
    1.28
     regularly
    1.26
     UN
    1.24
     corporate
    1.24
     comprehensively
    1.23
     promptly
    1.23
    handleChange
    1.23
     Kyle
    1.21
    Activations Density 0.015%

    No Known Activations