© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10356
    Prev
    Next
    INDEX
    Explanations

    acted upon by

    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
    Negative Logits
    s
    3.62
    ы
    3.37
    了
    3.24
    ات
    3.14
    т
    3.08
    ся
    2.91
    ು
    2.81
    ا
    2.81
    ness
    2.80
    tains
    2.72
    POSITIVE LOGITS
    प्ताह
    2.39
    uger
    2.24
    ptide
    2.10
    obacillus
    2.06
    FL
    2.04
    ğa
    2.03
    Bu
    1.99
    त्मक
    1.95
     bru
    1.94
    pler
    1.93
    Activations Density 0.007%

    No Known Activations