© 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. 112791
    Prev
    Next
    INDEX
    Explanations

    initials like J.P.K. or J.L.P

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

    The neuron zeroes in on standalone uppercase-letter tokens (often with trailing periods) that mark authors’ or court‐citation initials in references.

    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
     cammino
    -1.69
     sogno
    -1.58
     two
    -1.52
     pensiero
    -1.50
     gemeinsamen
    -1.48
     any
    -1.44
     convite
    -1.44
    البته
    -1.41
     viaggio
    -1.41
     commentaires
    -1.40
    POSITIVE LOGITS
     who
    2.22
     have
    1.77
     said
    1.62
    遽
    1.51
    tyimages
    1.41
     butterknife
    1.40
    ėjo
    1.39
    yled
    1.36
     kteří
    1.36
    agerie
    1.34
    Activations Density 0.067%

    No Known Activations