© 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. 69909
    Prev
    Next
    INDEX
    Explanations

    html layout elements

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

    The neuron strongly activates on numeric tokens (e.g. grid‐size or style values) in the code, especially numbers in class names and inline CSS.

    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
    …”
    -2.19
     ”
    -2.16
    :
    -2.09
    b
    -2.06
     Through
    -2.05
     remove
    -1.95
    」、
    -1.94
    f
    -1.93
     Since
    -1.84
     Until
    -1.81
    POSITIVE LOGITS
    雱
    2.17
    ientras
    1.96
    karten
    1.95
    热血
    1.91
     ustedes
    1.91
    hehehe
    1.91
    ふと
    1.84
     $-$
    1.82
    出于
    1.81
    kalender
    1.80
    Activations Density 0.001%

    No Known Activations