© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118857
    Prev
    Next
    INDEX
    Explanations

    screen border appearance

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

    The neuron flags any token that isn’t plain common English letters—e.g. Chinese characters, digits, or other non-Latin symbols.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    patrón
    -0.90
     niž
    -0.77
    icians
    -0.72
    了一遍
    -0.71
    sólo
    -0.71
     marcada
    -0.71
     revanche
    -0.71
     vayas
    -0.71
     explosión
    -0.70
     Völker
    -0.69
    POSITIVE LOGITS
     bezel
    1.47
     border
    1.34
    border
    1.22
     bez
    1.20
     BORDER
    1.12
     borders
    1.08
    ไร
    1.05
     Border
    1.05
    BORDER
    1.04
    bez
    1.02
    Activations Density 0.018%

    No Known Activations