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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3723
    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
     czy
    1.04
     oder
    1.00
     or
    0.95
     voto
    0.90
     eller
    0.90
     쓰는
    0.82
     başka
    0.79
     (
    0.77
     implic
    0.77
    <eos>
    0.77
    POSITIVE LOGITS
     многочис
    1.44
     светло
    1.26
    nesses
    1.22
     मार्गों
    1.22
    avourites
    1.18
     তন্ম
    1.18
    onnay
    1.18
     Mendes
    1.17
     moieties
    1.17
    atho
    1.17
    Activations Density 0.085%

    No Known Activations