© 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. 34-GEMMASCOPE-RES-131K
    7. 119245
    Prev
    Next
    INDEX
    Explanations

    states or actions completed

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

    The neuron strongly activates on occurrences of the verb “have” (and its present‐tense variant “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_34/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
     ersten
    -1.05
    ticamente
    -0.93
     acabado
    -0.92
    ancang
    -0.92
     ensimmä
    -0.91
     rostros
    -0.90
    {(
    -0.89
    istration
    -0.88
    meine
    -0.88
    最初に
    -0.88
    POSITIVE LOGITS
     been
    1.99
     become
    1.94
     found
    1.67
     a
    1.55
     recently
    1.48
    found
    1.40
     developed
    1.37
     lately
    1.34
     learned
    1.17
     tried
    1.16
    Activations Density 0.068%

    No Known Activations