© 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. 4039
    Prev
    Next
    INDEX
    Explanations

    Generally introducing typical characteristics

    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
    <bos>
    3.02
    𝑒
    2.78
    𝑟
    2.28
    𝑖
    2.25
    mute
    2.18
    お
    2.18
    an
    2.11
     Seniors
    2.11
     Optics
    2.09
    ვა
    2.08
    POSITIVE LOGITS
    webtoken
    2.64
    ерез
    2.64
    ﻋ
    2.54
    Vậy
    2.47
    توان
    2.39
    균
    2.37
    鹉
    2.36
    upaten
    2.36
    quers
    2.29
    PLATES
    2.29
    Activations Density 0.032%

    No Known Activations