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. 15130
    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
     permanently
    1.08
    ac
    1.05
    c
    1.02
    associated
    1.02
     of
    0.96
    is
    0.95
    :
    0.94
    ო
    0.93
    beat
    0.93
    of
    0.92
    POSITIVE LOGITS
     Lobkovic
    1.72
     chercheurs
    1.60
     komputer
    1.56
     viszont
    1.55
    Algorithms
    1.55
     ludzie
    1.54
     aluno
    1.53
     computador
    1.53
     Função
    1.53
     Ciência
    1.52
    Activations Density 0.000%

    No Known Activations