© 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. 7-GEMMASCOPE-2-RES-16K
    7. 120
    Prev
    Next
    INDEX
    Explanations

    Curriculum, bd, Tur

    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_7_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
     yield
    1.69
     S
    1.63
     fall
    1.61
    $/
    1.59
     sub
    1.56
    $\
    1.49
    J
    1.45
    ห
    1.43
     body
    1.40
    $
    1.37
    POSITIVE LOGITS
    πού
    1.98
    ávání
    1.98
    czna
    1.97
     rossa
    1.95
    glichen
    1.91
     świata
    1.87
     χωρίς
    1.87
    jupiter
    1.86
     poroz
    1.86
     pendapatan
    1.85
    Activations Density 0.000%

    No Known Activations