© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12203
    Prev
    Next
    INDEX
    Explanations

    SQL constraints and joins

    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
    俵
    2.15
    INavigation
    1.97
     semicol
    1.95
    రుగులు
    1.89
    𝙝
    1.87
    tiny
    1.85
     licenses
    1.85
     licences
    1.85
     throats
    1.84
    ตรา
    1.83
    POSITIVE LOGITS
    ówn
    1.76
     ق
    1.73
    ِ
    1.73
    owych
    1.64
    عدة
    1.60
    돕
    1.60
    ន៍
    1.60
    efeller
    1.59
    łac
    1.58
     suggesting
    1.56
    Activations Density 0.000%

    No Known Activations