© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10243
    Prev
    Next
    INDEX
    Explanations

    manipulation advice

    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_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
     άλ
    0.80
     marvel
    0.77
    숨
    0.75
    akwa
    0.74
    рак
    0.73
     obliv
    0.73
    pval
    0.71
    شكال
    0.70
    เหลือ
    0.70
     اقبال
    0.70
    POSITIVE LOGITS
     conducción
    1.08
     Chilli
    1.03
     நீண்ட
    1.02
     direcciones
    1.01
    䇞
    1.00
     Obispo
    0.99
     mantener
    0.99
     Spicy
    0.99
     longiore
    0.99
     Chaud
    0.97
    Activations Density 0.264%

    No Known Activations