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. 15131
    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
    ALLY
    1.33
    !";
    1.32
    "]["
    1.31
    ġ
    1.29
    लिये
    1.29
     enrollment
    1.26
     Analyzing
    1.25
     जाएँ
    1.24
     диагностики
    1.24
    "+
    1.23
    POSITIVE LOGITS
     lately
    1.23
     had
    1.14
     이에
    1.13
    되
    1.13
     therefore
    1.10
     quite
    1.09
     이번
    1.07
     bomb
    1.07
     최근
    1.06
     sadly
    1.05
    Activations Density 0.053%

    No Known Activations