© 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. 16140
    Prev
    Next
    INDEX
    Explanations

    has been

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

    The neuron fires strongly on occurrences of the auxiliary verb “has.”

    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
     and
    -2.45
    ázaro
    -2.25
    neling
    -2.22
    ledad
    -2.16
    alucía
    -2.16
    fordshire
    -2.14
    thodoxy
    -2.09
    nique
    -2.02
    ſam
    -1.98
    taya
    -1.95
    POSITIVE LOGITS
     been
    4.63
     become
    2.41
     
    2.39
     "
    2.23
    ’
    2.22
    nt
    2.13
    \
    2.06
     \
    2.00
     come
    1.98
    He
    1.90
    Activations Density 0.159%

    No Known Activations