© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12630
    Prev
    Next
    INDEX
    Explanations

    colors like yellow, purple, orange

    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_7_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
    鴦
    1.89
    ંત્ર
    1.88
    izio
    1.64
    zess
    1.64
     oscillating
    1.62
    ચ્
    1.60
     stroke
    1.60
    sleep
    1.60
     dehydration
    1.58
     duel
    1.58
    POSITIVE LOGITS
    на
    2.03
    嶙
    1.90
    a
    1.87
     Coinbase
    1.78
    ae
    1.77
    as
    1.77
    PayPal
    1.76
     architet
    1.74
     PayPal
    1.73
    รูป
    1.73
    Activations Density 0.059%

    No Known Activations