© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14050
    Prev
    Next
    INDEX
    Explanations

    work and career

    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
    க
    1.54
    kran
    1.49
     Model
    1.43
    திய
    1.41
    கர
    1.40
    tl
    1.33
    metre
    1.32
    s
    1.32
    startsWith
    1.29
     [
    1.29
    POSITIVE LOGITS
     polu
    1.66
     drogas
    1.63
     policiais
    1.58
    刑
    1.58
     encarg
    1.55
     citado
    1.55
     полицей
    1.54
    Corruption
    1.53
     narcot
    1.53
    滓
    1.53
    Activations Density 0.175%

    No Known Activations