© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101498
    Prev
    Next
    INDEX
    Explanations

    By followed by names

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

    The neuron detects attribution lines or bylines, i.e. header tokens like “From” or “By” that mark the author or poster.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    %;
    -1.78
    ☫
    -1.76
    took
    -1.72
     современной
    -1.70
     carcasa
    -1.70
    began
    -1.69
    铙
    -1.66
    这
    -1.66
     '-
    -1.63
    uttgart
    -1.60
    POSITIVE LOGITS
     our
    2.17
     some
    2.13
     both
    1.98
     many
    1.93
     that
    1.90
     those
    1.83
     people
    1.81
     their
    1.80
     this
    1.70
     each
    1.70
    Activations Density 0.001%

    No Known Activations