© 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. 104027
    Prev
    Next
    INDEX
    Explanations

    investigating and evaluating outcomes

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

    The neuron activates on numeric tokens, i.e. any numbers (including multi‐digit and decimal 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
     as
    -1.63
    _{
    -1.59
     not
    -1.58
    }_{
    -1.56
     first
    -1.55
     despite
    -1.41
    些什么
    -1.38
     etc
    -1.36
     still
    -1.34
     perhaps
    -1.33
    POSITIVE LOGITS
     veneno
    1.39
     remplacement
    1.38
     retours
    1.38
     appeler
    1.36
     bolsillo
    1.36
     doigts
    1.34
     comportements
    1.34
     він
    1.34
     afterward
    1.33
     symboles
    1.33
    Activations Density 0.248%

    No Known Activations