© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 3641
    Prev
    Next
    INDEX
    Explanations

    he she his her followed by actions

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

    The neuron responds strongly to personal pronouns (especially “he,” “she,” and “they”) and their related auxiliary or modal verbs.

    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
     is
    -1.76
     are
    -1.75
     you
    -1.70
    ,
    -1.59
     may
    -1.43
     we
    -1.40
     were
    -1.40
     There
    -1.36
     there
    -1.35
     style
    -1.35
    POSITIVE LOGITS
     tomto
    1.64
     їх
    1.55
    Примі
    1.52
     bascul
    1.51
    usually
    1.49
    Теперь
    1.49
    signable
    1.43
     mineures
    1.43
     家居
    1.38
     мужской
    1.38
    Activations Density 0.016%

    No Known Activations