© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7425
    Prev
    Next
    INDEX
    Explanations

    popular machine learning papers and techniques

    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
     inscr
    0.95
    记住
    0.93
     Suddenly
    0.91
    guessing
    0.90
     什么
    0.87
    붕
    0.86
     법칙
    0.86
     improb
    0.84
     பச
    0.84
     मोहन
    0.81
    POSITIVE LOGITS
     benchmarks
    1.03
     benchmark
    1.03
     runs
    0.96
     evaluations
    0.96
    篭
    0.96
     MATLAB
    0.96
    हिनी
    0.95
     evaluated
    0.93
     preliminary
    0.92
     evaluation
    0.92
    Activations Density 0.093%

    No Known Activations