Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 15418
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    s
    1.60
     abogados
    1.24
    y
    1.14
    らう
    1.14
    t
    1.10
    т
    1.09
     seper
    1.07
     abit
    1.07
     chave
    1.05
    ять
    1.04
    POSITIVE LOGITS
    சி
    1.75
    bbene
    1.60
    ɾ
    1.57
    andr
    1.52
    pyrimidine
    1.52
     Điều
    1.51
    内的
    1.50
    monary
    1.46
    رمپ
    1.46
    лет
    1.46
    Activations Density 0.017%

    No Known Activations