© 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. 9621
    Prev
    Next
    INDEX
    Explanations

    generating code structures

    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
    umn
    0.80
    utches
    0.77
    lev
    0.77
    sco
    0.76
    묘
    0.75
    িপুর
    0.71
     옮
    0.69
     micro
    0.68
    ես
    0.67
     Directions
    0.67
    POSITIVE LOGITS
    erçe
    1.00
     restraint
    0.99
    笺
    0.98
     laissent
    0.96
     açúcar
    0.96
     jä
    0.95
    Loksatta
    0.95
     generar
    0.95
     elkaar
    0.94
    assembled
    0.93
    Activations Density 0.080%

    No Known Activations