© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2788
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     vii
    1.05
     viii
    1.02
     
    1.02
     xii
    1.01
     
    0.99
     xvi
    0.95
     xiii
    0.95
     
    0.95
     ò
    0.93
                                 
    0.91
    POSITIVE LOGITS
    Autocomplete
    0.88
    Memento
    0.83
    Kabhi
    0.78
    Buscar
    0.75
    AutoComplete
    0.75
    Closeup
    0.74
    BuildConfig
    0.74
    Picklist
    0.73
    Repost
    0.73
    Pinterest
    0.73
    Activations Density 0.361%

    No Known Activations