© 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. 22-GEMMASCOPE-RES-131K
    7. 72166
    Prev
    Next
    INDEX
    Explanations

    he's + verb/adverb

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

    The neuron fires on finite (inflected) English verbs (e.g. third-person singular and past tense forms) that mark tense or agreement.

    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
     its
    -1.88
     itself
    -1.59
     manicura
    -1.49
     decoracion
    -1.43
    我了
    -1.40
     who
    -1.38
     ważne
    -1.35
     soldadura
    -1.35
     bricolaje
    -1.34
     '\\;'
    -1.33
    POSITIVE LOGITS
     to
    1.92
     himself
    1.45
     \
    1.45
     /*
    1.38
    himself
    1.31
     fallu
    1.26
    IZONA
    1.22
     "
    1.19
    Ｄ
    1.18
        
    1.17
    Activations Density 0.110%

    No Known Activations