© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 928
    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
    
    1.60
     entidad
    1.53
     misi
    1.51
     autobús
    1.50
     kú
    1.49
    ása
    1.49
     zakl
    1.48
     rámci
    1.48
    <unused735>
    1.47
    iyordu
    1.47
    POSITIVE LOGITS
    oretically
    1.67
    spapers
    1.51
    xiety
    1.51
    ories
    1.46
    ো
    1.45
    hibition
    1.41
    mselves
    1.40
    fection
    1.39
    tains
    1.39
    spaper
    1.39
    Activations Density 1.024%

    No Known Activations