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. 3621
    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
    義務
    1.60
    antry
    1.49
     Occasionally
    1.44
     Кре
    1.43
     Lubric
    1.42
    вис
    1.42
    簌
    1.41
    颇
    1.40
     Crus
    1.39
    此前
    1.39
    POSITIVE LOGITS
    n
    1.36
    run
    1.31
     enkelt
    1.28
    na
    1.26
     kada
    1.24
    koliko
    1.23
     ja
    1.19
    sinya
    1.17
     jedno
    1.16
    kta
    1.16
    Activations Density 0.003%

    No Known Activations