© 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. 106103
    Prev
    Next
    INDEX
    Explanations

    TR /

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

    The neuron strongly activates on exception‐handling keywords (in particular “catch” in code).

    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
    beq
    -0.69
     Schaden
    -0.68
    alib
    -0.66
    狐
    -0.66
     Stirn
    -0.64
    大师
    -0.64
    არი
    -0.63
    gos
    -0.63
     gee
    -0.63
    mern
    -0.63
    POSITIVE LOGITS
     Chavez
    0.73
    geschlossen
    0.72
    Lähteet
    0.69
     ambiguous
    0.68
    🖼
    0.68
     amines
    0.67
    lová
    0.65
     ambiguity
    0.65
     アイテム
    0.65
    tvr
    0.65
    Activations Density 0.063%

    No Known Activations