© 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
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9835
    Prev
    Next
    INDEX
    Explanations

    per followed by -pendicular, -fection, -ishable, -ceived, -forms

    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
     arka
    1.03
    গুলিকে
    0.92
     कद
    0.90
     dak
    0.87
     hlad
    0.85
    img
    0.85
     onlar
    0.84
    ('/
    0.83
     dou
    0.83
    bled
    0.83
    POSITIVE LOGITS
     раствора
    1.03
     dynamical
    0.96
     fixtures
    0.90
    кона
    0.89
    locality
    0.89
     geometrically
    0.88
    relativistic
    0.88
     spectrosc
    0.87
    SOFTWARE
    0.87
     नाबाद
    0.87
    Activations Density 0.038%

    No Known Activations