© 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. 10622
    Prev
    Next
    INDEX
    Explanations

    percentages and probability

    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
    jö
    0.87
     പ്രത്യേക
    0.86
    scape
    0.83
     =-\
    0.83
     posled
    0.83
    zhou
    0.81
    잔
    0.81
     traz
    0.80
     గత
    0.80
     nổi
    0.79
    POSITIVE LOGITS
    <0xD8>
    1.59
    েরই
    1.21
     emissivity
    1.08
     humidity
    1.07
     доля
    1.05
     chance
    1.04
    efficiency
    1.03
     incline
    1.00
     ক্ষেত্রেই
    1.00
    ाइल
    0.99
    Activations Density 0.092%

    No Known Activations