© 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. 10-GEMMASCOPE-RES-131K
    7. 22673
    Prev
    Next
    INDEX
    Explanations

    attribution by name

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

    The neuron detects byline and photo‐credit labels (e.g. “Story By,” “Photos by,” “Photography by,” “photograph by”).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     baumwolle
    -1.71
     perfons
    -1.69
     LABOR
    -1.65
     ORCH
    -1.63
     feveral
    -1.62
     navegando
    -1.61
     URBAN
    -1.60
     OREGON
    -1.59
     moft
    -1.59
     ANNE
    -1.59
    POSITIVE LOGITS
     Therefore
    1.78
     With
    1.73
     anderen
    1.70
     โดย
    1.68
     However
    1.66
     Again
    1.63
    :
    1.62
     Each
    1.61
     Either
    1.61
     As
    1.60
    Activations Density 0.025%

    No Known Activations