© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77052
    Prev
    Next
    INDEX
    Explanations

    degree of attention

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

    The neuron fires on words that express quantity, degree, or extent—i.e. quantifiers and evaluative modifiers (like “lot,” “any,” “much,” “little,” “fair,” “same,” etc.).

    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
    眼前的
    -1.03
     Aralık
    -0.88
     месе
    -0.84
    INOIS
    -0.81
     KNOWLEDGE
    -0.79
    keyup
    -0.77
     Haziran
    -0.76
     encapsulated
    -0.75
     Donc
    -0.75
     olan
    -0.75
    POSITIVE LOGITS
     attention
    2.69
    attention
    1.77
    Attention
    1.74
     treatment
    1.66
     consideration
    1.60
     aandacht
    1.57
     coverage
    1.50
     Attention
    1.47
     scrutiny
    1.46
    attenzione
    1.46
    Activations Density 0.064%

    No Known Activations