© 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. 4107
    Prev
    Next
    INDEX
    Explanations

    reference

    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>
    3.08
    rr
    2.47
    nym
    2.41
    tri
    2.35
    tes
    2.31
     علمی
    2.21
    yp
    2.16
     przeci
    2.15
    rid
    2.15
     k
    2.15
    POSITIVE LOGITS
    ,*/}
    3.39
    BibitemOpen
    3.33
    䐍
    3.32
    <unused1648>
    3.30
    ંને
    3.30
    হন
    3.27
    衊
    3.26
    <unused1658>
    3.23
    <unused2189>
    3.21
    <unused544>
    3.20
    Activations Density 0.085%

    No Known Activations