© 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. 22-GEMMASCOPE-RES-131K
    7. 38767
    Prev
    Next
    INDEX
    Explanations

    names followed by punctuation

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

    This neuron detects personal names (proper‐noun tokens) in email or message text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     our
    -1.25
     unserer
    -1.05
     not
    -1.01
     ne
    -0.97
     Very
    -0.96
     ourselves
    -0.96
     It
    -0.94
    ૪
    -0.94
     Specific
    -0.93
     F
    -0.91
    POSITIVE LOGITS
     kysy
    1.23
     descendre
    1.14
     yrity
    1.14
     appeler
    1.10
     icônes
    1.09
     sélectionner
    1.08
     määrä
    1.04
     publier
    1.02
     CONSE
    1.01
     rafra
    1.01
    Activations Density 0.018%

    No Known Activations