© 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-65K
    7. 597
    Prev
    Next
    INDEX
    Explanations

    crucial /ˈcrucially/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    1.09
     quick
    0.97
     cl
    0.90
     d
    0.89
     s
    0.89
     .
    0.87
     st
    0.86
     the
    0.84
     f
    0.84
     man
    0.80
    POSITIVE LOGITS
     portavoz
    1.51
     configuración
    1.50
     vezes
    1.49
     Chayin
    1.48
     hidrográf
    1.46
     inoxyd
    1.46
     Pusenk
    1.44
     Lobkovic
    1.44
     zcela
    1.43
     ámbitos
    1.43
    Activations Density 0.212%

    No Known Activations