© 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. 35792
    Prev
    Next
    INDEX
    Explanations

    listing items with and or

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

    This neuron detects numerical tokens (digits or counts) 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_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
     allerlei
    -1.65
     diverses
    -1.41
     studenten
    -1.38
     verhind
    -1.38
     diriger
    -1.34
    鶿
    -1.30
    various
    -1.27
    鸱
    -1.27
    dames
    -1.23
    kkkk
    -1.20
    POSITIVE LOGITS
     Each
    1.48
     After
    1.43
     Every
    1.39
     There
    1.28
     after
    1.28
    Each
    1.27
    </strong>
    1.27
     had
    1.25
     has
    1.23
     unique
    1.17
    Activations Density 0.098%

    No Known Activations