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. 4061
    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
    ي
    2.47
    er
    2.41
    ت
    2.21
    加坡
    2.18
    ০
    1.97
    ی
    1.97
    hong
    1.84
    ا
    1.81
    ر
    1.81
    ing
    1.81
    POSITIVE LOGITS
    Читати
    1.58
     s
    1.42
     catap
    1.37
    пление
    1.37
     rectum
    1.35
    диться
    1.33
    quot
    1.33
    jacobian
    1.30
    пления
    1.29
     négl
    1.28
    Activations Density 0.000%

    No Known Activations