© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62875
    Prev
    Next
    INDEX
    Explanations

    competition results

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

    The neuron strongly activates on Spanish tokens—especially those carrying accents or langue‐specific words—marking spans of Spanish‐language text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    handmade
    -0.75
    Kinder
    -0.73
    Caitlin
    -0.69
    striker
    -0.69
    inno
    -0.69
    кипе
    -0.69
    кову
    -0.69
     yazı
    -0.66
     europea
    -0.66
    Thé
    -0.65
    POSITIVE LOGITS
    ihnachten
    0.86
     tournaments
    0.79
     zonal
    0.75
     украин
    0.75
    LocationManager
    0.74
    itaji
    0.73
     оба
    0.72
    éroport
    0.71
     Tark
    0.70
     Hend
    0.69
    Activations Density 0.037%

    No Known Activations