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. 15401
    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
    ্তা
    2.54
    ies
    1.82
    နှုန်း
    1.81
     successivement
    1.79
    perature
    1.78
     pente
    1.73
    नाथ
    1.73
    ບ
    1.72
    ikat
    1.65
    ahs
    1.64
    POSITIVE LOGITS
    s
    2.56
    DarkMode
    2.41
    ske
    2.40
    sman
    2.39
     nhiệm
    2.33
    utérus
    2.32
    sak
    2.29
    soci
    2.24
    INER
    2.23
    sar
    2.21
    Activations Density 0.003%

    No Known Activations