© 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. 10126
    Prev
    Next
    INDEX
    Explanations

    S&P 500

    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
    SOFTWARE
    1.54
     sıra
    1.53
    Butterfly
    1.51
    ra
    1.50
     그래서
    1.48
     راحت
    1.48
    끊
    1.47
     Biss
    1.47
     போய்
    1.46
     ssl
    1.43
    POSITIVE LOGITS
     medir
    1.63
     denominators
    1.62
    okes
    1.60
     figures
    1.56
    currentToken
    1.54
     tally
    1.53
    榖
    1.53
     oxen
    1.53
     figure
    1.52
    jsonObject
    1.52
    Activations Density 0.030%

    No Known Activations