© 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. 10-GEMMASCOPE-RES-131K
    7. 111840
    Prev
    Next
    INDEX
    Explanations

    `.Column height` binding

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

    The neuron fires on numeric literal tokens (especially decimal numbers) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     desmotiv
    -1.56
     however
    -1.51
     olika
    -1.42
     each
    -1.39
     decorada
    -1.37
     viktigt
    -1.36
     dificuldades
    -1.35
     favorece
    -1.35
     zwłaszcza
    -1.35
     särsk
    -1.34
    POSITIVE LOGITS
     on
    1.84
    我們
    1.66
    𝐞
    1.51
    1.39
     sebelum
    1.35
     nasional
    1.33
    lossen
    1.30
    我们
    1.27
    currents
    1.27
    тни
    1.23
    Activations Density 0.011%

    No Known Activations