© 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. 87248
    Prev
    Next
    INDEX
    Explanations

    holding or holds

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

    The neuron strongly fires on very high‐frequency, low‐content tokens—especially common function words like “of,” “to,” “like,” and similar stopwords.

    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
    లాలు
    -0.74
    pinas
    -0.70
    λογία
    -0.69
    داء
    -0.66
    ⃟
    -0.65
    carlo
    -0.65
    ziesz
    -0.64
    цией
    -0.64
    доби
    -0.64
    ospatial
    -0.61
    POSITIVE LOGITS
     holding
    6.84
     hold
    5.66
    Holding
    5.63
    holding
    5.41
     Holding
    5.38
     holds
    5.19
     HOLD
    4.88
    Hold
    4.75
     held
    4.66
     Hold
    4.59
    Activations Density 0.085%

    No Known Activations