© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34916
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

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

    The neuron selectively activates on digits and arithmetic symbols, effectively identifying numeric constants and operators in formulas 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_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
     azulejos
    -1.19
     bluza
    -1.18
     cinqu
    -1.15
    faccia
    -1.13
    ebab
    -1.12
     produkt
    -1.11
    dekat
    -1.07
    ceda
    -1.05
    BoxShadow
    -1.04
    ceff
    -1.03
    POSITIVE LOGITS
    2
    1.61
    8
    1.59
    1
    1.57
    9
    1.48
    4
    1.41
    3
    1.40
    6
    1.33
    7
    1.28
    0
    1.21
    5
    1.17
    Activations Density 0.124%

    No Known Activations