© 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. 22-GEMMASCOPE-2-RES-16K
    4. 10638
    Prev
    Next
    INDEX
    Explanations

    powershell commands

    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_22_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
     Kasper
    0.99
     Wight
    0.95
     Wilkins
    0.92
     Schmitz
    0.92
    翁
    0.91
     Clinton
    0.91
     Gel
    0.89
    Clinton
    0.89
     Garrison
    0.88
    威尔
    0.87
    POSITIVE LOGITS
     ced
    0.95
    cedence
    0.89
    ﺲ
    0.88
    irection
    0.78
     Cev
    0.75
    ższe
    0.74
     breakage
    0.72
    เลต
    0.71
    nancy
    0.71
     flattened
    0.71
    Activations Density 0.033%

    No Known Activations