© 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. 15460
    Prev
    Next
    INDEX
    Explanations

    pets, insurance, crypto, health

    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
    ى
    1.16
    Look
    1.00
    most
    1.00
    äre
    0.99
    ará
    0.98
    owo
    0.97
    പൊ
    0.97
     বেঁ
    0.96
    Travelling
    0.96
    outed
    0.95
    POSITIVE LOGITS
     imgs
    1.65
     organism
    1.61
     platelet
    1.59
     фев
    1.57
     치료
    1.57
    齎
    1.54
    胃
    1.54
     病
    1.52
     biosolids
    1.51
    ammatory
    1.51
    Activations Density 0.000%

    No Known Activations