© 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. 34-GEMMASCOPE-RES-131K
    4. 84137
    Prev
    Next
    INDEX
    Explanations

    location start indices

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

    The neuron strongly activates on numeric tokens (digit sequences representing numbers) in structured data or code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     compositeur
    -0.75
    éf
    -0.73
     nomenclature
    -0.69
     نیاز
    -0.68
    Inhalt
    -0.66
     afirmó
    -0.66
    сторон
    -0.65
    ulsory
    -0.65
    ISTR
    -0.64
    Dish
    -0.64
    POSITIVE LOGITS
     location
    1.85
     locations
    1.59
     position
    1.51
     ubicación
    1.46
     getLocation
    1.45
     Location
    1.44
    位置
    1.40
     positions
    1.38
     위치
    1.38
     loc
    1.37
    Activations Density 0.045%

    No Known Activations