© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63994
    Prev
    Next
    INDEX
    Explanations

    mathematical and statistical concepts

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

    The neuron fires on inline mathematical notation and highly technical math terms—especially LaTeX‐style markers (dollar signs, Greek names like “sigma,” hyphens) and math‐specific vocabulary.

    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
     interfaz
    -0.88
     sàn
    -0.87
    ographically
    -0.80
    corpo
    -0.77
     isInitialized
    -0.76
    Joystick
    -0.75
     missão
    -0.74
     privind
    -0.74
     yaris
    -0.74
     chuy
    -0.74
    POSITIVE LOGITS
     Vap
    1.45
     VC
    1.30
    VC
    1.18
     vc
    0.94
     Dudley
    0.92
     Sauer
    0.82
    vc
    0.82
    ronym
    0.77
     subgraph
    0.76
     vap
    0.74
    Activations Density 0.030%

    No Known Activations