© 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. 4144
    Prev
    Next
    INDEX
    Explanations

    language initialization

    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
    u
    1.72
    ي
    1.50
    an
    1.43
    i
    1.28
    at
    1.19
    y
    1.18
    in
    1.11
    uine
    1.10
    en
    1.10
    uaries
    1.09
    POSITIVE LOGITS
    OPTV
    1.91
     미술
    1.90
     socketList
    1.86
    स्पी
    1.85
     彩
    1.83
    Seqlist
    1.83
    Maple
    1.83
    ReferencePose
    1.83
    睍
    1.81
    λαβ
    1.80
    Activations Density 0.072%

    No Known Activations