© 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. 4162
    Prev
    Next
    INDEX
    Explanations

    military contexts

    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
    y
    2.83
    u
    2.70
    n
    2.65
    ed
    2.57
    nacht
    2.56
    in
    2.49
    en
    2.46
    nå
    2.43
    id
    2.25
    ي
    2.18
    POSITIVE LOGITS
    䣬
    3.07
    <unused542>
    3.05
    $>$
    2.98
     directives
    2.96
    ロッパ
    2.92
     feuille
    2.91
     Humble
    2.90
    <unused1766>
    2.84
    㴦
    2.82
     Уи
    2.79
    Activations Density 0.019%

    No Known Activations