© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84185
    Prev
    Next
    INDEX
    Explanations

    don't have

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

    The neuron strongly activates on occurrences of the verb “have,” especially in contexts like “I don’t have…” or “Does X have….”

    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
    튿
    -1.63
    ícias
    -1.61
     tournoi
    -1.56
    說
    -1.50
     mauva
    -1.48
    庒
    -1.44
     纹身
    -1.42
    峮
    -1.42
    viano
    -1.41
     Reſ
    -1.41
    POSITIVE LOGITS
     any
    3.75
     anymore
    2.33
     anything
    2.06
     &
    1.97
     to
    1.84
     or
    1.75
     which
    1.75
     ANY
    1.74
     time
    1.70
    </strong>
    1.67
    Activations Density 0.027%

    No Known Activations