© 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. 22-GEMMASCOPE-RES-131K
    4. 40184
    Prev
    Next
    INDEX
    Explanations

    mathematical questions and calculations

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

    The neuron is responding to question‐ending punctuation (i.e. it fires on “?” tokens).

    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
     kram
    -1.27
     urat
    -1.23
     effek
    -1.23
     stoff
    -1.23
     contraire
    -1.22
     kanton
    -1.21
     valla
    -1.19
     kiz
    -1.18
     vek
    -1.18
     merk
    -1.17
    POSITIVE LOGITS
     How
    1.42
     how
    1.39
     with
    1.38
     What
    1.27
     help
    1.13
     dotyczą
    1.12
    elegante
    1.10
    <>();
    
    1.09
    umato
    1.08
    院校
    1.07
    Activations Density 0.084%

    No Known Activations