© 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. 10-GEMMASCOPE-RES-131K
    7. 85793
    Prev
    Next
    INDEX
    Explanations

    titles or proper nouns

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

    The neuron consistently lights up on numerical tokens (digits and numeric values) in the text.

    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
     that
    -1.86
    </em>
    -1.84
     this
    -1.47
     introduce
    -1.41
     not
    -1.35
     nächste
    -1.35
     now
    -1.31
     those
    -1.30
    fizierung
    -1.27
     your
    -1.26
    POSITIVE LOGITS
    ઞ
    1.53
     韩
    1.46
    ২
    1.45
    ttää
    1.42
     jepang
    1.41
     barne
    1.41
    inä
    1.39
    Rather
    1.39
     thèmes
    1.39
     Chriſt
    1.38
    Activations Density 0.025%

    No Known Activations