© 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. 107098
    Prev
    Next
    INDEX
    Explanations

    analysis and explanation

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

    The neuron activates on numeric tokens (e.g. counts, percentages, and other numbers).

    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
    Rote
    -0.78
    摇了摇头
    -0.74
     retiro
    -0.72
     secours
    -0.72
    Campe
    -0.71
    achts
    -0.70
     haga
    -0.69
    Hamburger
    -0.69
    Guarda
    -0.69
     söyle
    -0.69
    POSITIVE LOGITS
     explained
    1.89
     Explained
    1.65
     explain
    1.52
    explained
    1.50
     explaining
    1.45
     Explains
    1.36
     explains
    1.35
     cumulative
    1.26
     Explain
    1.21
    Kaiser
    1.19
    Activations Density 0.012%

    No Known Activations