© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16450
    Prev
    Next
    INDEX
    Explanations

    actions leading to a state

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

    The neuron fires on verbs—tokens representing actions or states (e.g. see, using, created, build, burn, receive, am, supply, submit, made).

    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
     récol
    -1.41
     rencont
    -1.29
     gordura
    -1.27
    especial
    -1.25
    多かった
    -1.23
     comportements
    -1.23
     Алла
    -1.20
    際には
    -1.20
     gebeten
    -1.20
    ままで
    -1.18
    POSITIVE LOGITS
     is
    3.30
     are
    2.94
     was
    2.38
     will
    2.17
     would
    1.84
     could
    1.80
     wouldn
    1.67
     may
    1.66
     here
    1.66
     wasn
    1.65
    Activations Density 0.055%

    No Known Activations