© 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. 4064
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation or definition

    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
     ดัง
    1.24
    EDA
    1.20
    🍉
    1.17
    👑
    1.16
     ตั้ง
    1.15
    벨
    1.14
    💕
    1.14
    รส
    1.13
     सीड
    1.12
     รุ่น
    1.12
    POSITIVE LOGITS
     lavoro
    1.08
     Ingle
    1.02
     commuting
    0.99
     belang
    0.98
     miscellaneous
    0.97
     trabalho
    0.95
     telephones
    0.94
     employ
    0.94
     Croydon
    0.94
     téléphonique
    0.93
    Activations Density 0.300%

    No Known Activations