© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1454
    Prev
    Next
    INDEX
    Explanations

    list item numbering

    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
     refrigerant
    1.72
    ູ້
    1.66
    ven
    1.65
    isting
    1.62
     hob
    1.52
    ars
    1.50
    aggio
    1.48
    匀
    1.45
    <bos>
    1.44
     stagger
    1.44
    POSITIVE LOGITS
    TouchEvent
    2.04
     Elm
    1.96
    ی
    1.91
     adına
    1.86
    Tay
    1.85
     डूब
    1.84
     hakkında
    1.84
    ılarak
    1.84
    Gate
    1.84
    Apps
    1.76
    Activations Density 0.016%

    No Known Activations