© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102419
    Prev
    Next
    INDEX
    Explanations

    finding specific values or items

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

    The neuron activates on the imperative or directive verbs that lead off math problem statements (e.g. “Let,” “Using,” “Suppose,” “Find,” “Determine”).

    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
     
    -1.58
     know
    -1.57
     than
    -1.41
    懂得
    -1.40
     Builds
    -1.40
     you
    -1.38
    }\
    -1.38
    ”
    -1.34
     possess
    -1.33
    )
    -1.33
    POSITIVE LOGITS
     the
    1.77
    красивые
    1.62
    źródło
    1.54
     pantalon
    1.49
     palme
    1.49
    Какие
    1.48
    комплект
    1.46
    Экономи
    1.44
    jando
    1.41
    Jadi
    1.41
    Activations Density 0.107%

    No Known Activations