© 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. 54067
    Prev
    Next
    INDEX
    Explanations

    names joined by and

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

    This neuron detects numeric tokens (digits or numbers) 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
     quando
    -1.27
     loro
    -1.23
    岀
    -1.18
     Lesnar
    -1.16
     indica
    -1.16
     denominada
    -1.13
    zmán
    -1.12
     ihren
    -1.11
     Leaven
    -1.09
     algunos
    -1.08
    POSITIVE LOGITS
    醅
    1.35
    Dá
    1.26
    jelaskan
    1.23
    ofing
    1.23
    !(:
    1.16
    ası
    1.15
     his
    1.15
     who
    1.14
     jaunes
    1.13
    quien
    1.11
    Activations Density 0.045%

    No Known Activations