© 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. 9683
    Prev
    Next
    INDEX
    Explanations

    Ryzen and CNN/GAN

    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
     alumni
    0.96
     Dogg
    0.93
     LOD
    0.92
     retr
    0.91
     LAD
    0.90
     anos
    0.89
    간
    0.87
    凌晨
    0.87
     pube
    0.86
     aik
    0.86
    POSITIVE LOGITS
    align
    1.07
    minipage
    1.03
    center
    0.99
    वाड़ा
    0.98
    োনায়
    0.97
    onces
    0.95
    ものである
    0.93
    eqnarray
    0.92
    akse
    0.90
     Sammlung
    0.90
    Activations Density 0.002%

    No Known Activations