© 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. 2671
    Prev
    Next
    INDEX
    Explanations

    programming and international words

    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
    𝓇
    2.76
    ాన
    2.58
    াভাবিক
    2.56
    ultats
    2.53
    ிர்
    2.36
    <bos>
    2.35
    UInt
    2.32
    н
    2.31
    ารย์
    2.30
    ibban
    2.28
    POSITIVE LOGITS
    ty
    2.77
    瘩
    2.47
    ment
    2.43
    ঁজ
    2.31
    ="#!"
    2.22
    न्ट
    2.20
    ggio
    2.13
    ]".
    2.10
    ccion
    2.06
    có
    2.05
    Activations Density 0.439%

    No Known Activations