© 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. 207112
    Prev
    Next
    INDEX
    Explanations

    words indicating location or sequence

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

    Raises ValueError or uuid

    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
     எலும்
    0.50
    <unused3>
    0.48
    <unused41>
    0.48
     carbohydrates
    0.48
    ிகளின்
    0.47
    Buffered
    0.47
    Cuánto
    0.47
     அறிக
    0.46
     సంవత్స
    0.46
    혐
    0.46
    POSITIVE LOGITS
     instalar
    0.56
     questo
    0.53
     pleases
    0.52
     I
    0.52
     personalizar
    0.52
    I
    0.51
     installing
    0.50
     instalado
    0.48
     installé
    0.48
    jenigen
    0.47
    Activations Density 0.002%

    No Known Activations