© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6850
    Prev
    Next
    INDEX
    Explanations

    how many nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    部份
    1.98
    '):
    1.94
     komun
    1.93
     semua
    1.91
     partito
    1.90
    :')
    1.84
     riguardo
    1.84
    grado
    1.77
    ’:
    1.75
    ?')
    1.74
    POSITIVE LOGITS
     Stunden
    1.51
     gallons
    1.38
    キロ
    1.37
    middot
    1.34
     litres
    1.33
    |}{
    1.31
    hadow
    1.29
     darn
    1.29
     impressions
    1.26
     Hours
    1.24
    Activations Density 0.099%

    No Known Activations