© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98938
    Prev
    Next
    INDEX
    Explanations

    separating clauses or phrases

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

    The neuron strongly activates on numeric tokens—especially floating‐point numbers (digits with decimals).

    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
     två
    -1.52
    </strong>
    -1.42
     boister
    -1.39
     crucial
    -1.37
     specif
    -1.34
    >
    -1.34
     DIFFERENT
    -1.32
     breathtaking
    -1.31
     andere
    -1.30
     absurd
    -1.30
    POSITIVE LOGITS
     there
    1.81
     if
    1.70
     EVERY
    1.54
     Certainly
    1.51
     this
    1.48
     people
    1.48
     Combining
    1.46
     Honestly
    1.44
     seems
    1.40
     certainly
    1.39
    Activations Density 0.294%

    No Known Activations