© 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. 10-GEMMASCOPE-RES-131K
    7. 7840
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating action

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

    The main thing this neuron does is detect past‐tense or past‐participle verb forms.

    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
     you
    -1.77
     nuestro
    -1.61
     anyone
    -1.38
     laquelle
    -1.35
     nostra
    -1.35
     our
    -1.33
     furious
    -1.33
     secondo
    -1.31
     cómod
    -1.30
     ESPECIAL
    -1.30
    POSITIVE LOGITS
     who
    1.66
    картинка
    1.65
     about
    1.59
     instead
    1.55
     and
    1.52
     nuoc
    1.43
    visite
    1.36
     thuy
    1.34
     to
    1.34
     again
    1.32
    Activations Density 0.109%

    No Known Activations