© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56715
    Prev
    Next
    INDEX
    Explanations

    office hours

    np_acts-logits-general · gemini-2.5-flash-lite

    truck, Italy, soldier, most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    เนิน
    0.46
    sen
    0.43
     invoices
    0.43
    ка
    0.41
    aft
    0.41
    $'
    0.41
    ў
    0.41
    lated
    0.41
    â
    0.41
     invoice
    0.40
    POSITIVE LOGITS
     comandante
    0.50
     Sélection
    0.46
     négy
    0.46
     normativa
    0.45
    Aless
    0.45
     algunos
    0.45
     normales
    0.45
     Recreational
    0.44
     conquistar
    0.44
     resaltar
    0.44
    Activations Density 0.000%

    No Known Activations