© 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. 66696
    Prev
    Next
    INDEX
    Explanations

    standard approaches and models

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

    The neuron detects terms referring to conventional or canonical scientific frameworks (e.g. “standard,” “classical,” “typical,” “expected”).

    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
     vooral
    -1.91
     první
    -1.66
    subsec
    -1.49
     nových
    -1.48
     čern
    -1.48
     každého
    -1.47
     misschien
    -1.46
     lepší
    -1.44
     všechny
    -1.38
     bijna
    -1.38
    POSITIVE LOGITS
    now
    1.75
     techniques
    1.59
     now
    1.59
     like
    1.46
     maintenant
    1.43
     methods
    1.40
    ”？
    1.39
     Now
    1.38
    not
    1.37
    you
    1.35
    Activations Density 0.120%

    No Known Activations