© 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. 10-GEMMASCOPE-RES-131K
    7. 14140
    Prev
    Next
    INDEX
    Explanations

    case citations and code snippets

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

    This neuron identifies numeric line‐number specifications in unified diff (patch) hunk headers.

    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
     diminuer
    -1.55
    ейчас
    -1.51
     gefe
    -1.48
     марта
    -1.45
    estaw
    -1.41
    Архи
    -1.40
    Hochspringen
    -1.40
     discuter
    -1.39
     августа
    -1.38
    忪
    -1.38
    POSITIVE LOGITS
    the
    1.64
    you
    1.64
    your
    1.39
     it
    1.39
     you
    1.33
    they
    1.33
    </b>
    1.30
    we
    1.29
    for
    1.25
    You
    1.25
    Activations Density 0.002%

    No Known Activations