© 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. 10429
    Prev
    Next
    INDEX
    Explanations

    root paths and create commands

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Z
    1.18
    B
    1.15
    agro
    1.13
    --
    1.09
     gallery
    1.08
    公里
    1.06
    —
    1.05
    ↵
    1.05
    sp
    1.04
    -
    1.03
    POSITIVE LOGITS
    <unused1640>
    1.98
    <unused952>
    1.92
     Borrower
    1.90
    贰百
    1.89
    <unused2004>
    1.84
    <unused1202>
    1.83
    壹百
    1.83
    <unused1866>
    1.83
    氻
    1.83
     Bradbury
    1.81
    Activations Density 0.017%

    No Known Activations