© 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. 11389
    Prev
    Next
    INDEX
    Explanations

    introduces a reason

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

    The neuron is detecting causal connectives—that is, words introducing reasons (e.g. “because,” “so,” “coz,” 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_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
     murieron
    -1.66
    ཫ
    -1.64
    分かります
    -1.55
     także
    -1.52
     همچنین
    -1.50
    همچنین
    -1.49
     também
    -1.48
     désactiv
    -1.44
    勠
    -1.44
     détru
    -1.41
    POSITIVE LOGITS
     this
    1.66
     what
    1.56
    1.49
     who
    1.48
    .
    1.38
     like
    1.34
    ‘
    1.34
    žel
    1.33
     zahlreiche
    1.27
    ddagger
    1.26
    Activations Density 0.019%

    No Known Activations