© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73699
    Prev
    Next
    INDEX
    Explanations

    period followed by new sentence/code

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

    This neuron activates on numeric literals (digits) in code or comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    lifter
    -0.95
    knew
    -0.93
     vérit
    -0.93
    flour
    -0.93
     که
    -0.93
    swire
    -0.93
    álni
    -0.92
    wheres
    -0.92
    వా
    -0.92
     dátum
    -0.91
    POSITIVE LOGITS
     to
    1.48
     if
    1.14
     may
    1.13
     has
    1.03
    </td>
    0.97
     seluruh
    0.96
    viewpager
    0.94
    enang
    0.93
    üstü
    0.93
     sonrası
    0.91
    Activations Density 0.023%

    No Known Activations