© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2261
    Prev
    Next
    INDEX
    Explanations

    print statements

    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_13_width_65k_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
     part
    1.03
     tap
    0.97
    ,
    0.96
     lot
    0.91
     I
    0.90
     reap
    0.90
     heft
    0.87
     tract
    0.86
     divid
    0.84
     lit
    0.84
    POSITIVE LOGITS
    ủa
    1.62
    ônio
    1.55
    őtt
    1.54
    शंकर
    1.52
     další
    1.51
    अन्य
    1.50
    incón
    1.49
    কল্যা
    1.47
    álního
    1.47
    <unused1285>
    1.46
    Activations Density 0.014%

    No Known Activations