© 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. 14085
    Prev
    Next
    INDEX
    Explanations

    reverse order

    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
    н
    3.33
    s
    3.18
    !='')
    3.15
    ië
    3.00
    푐
    2.79
    ので
    2.78
    ン
    2.76
    tow
    2.70
     !='')
    2.69
    ଗ
    2.66
    POSITIVE LOGITS
    pes
    2.06
    mland
    2.05
    čne
    1.93
    pora
    1.91
    hten
    1.87
    ष
    1.82
    uding
    1.73
    疇
    1.68
    pping
    1.67
    Й
    1.66
    Activations Density 0.000%

    No Known Activations