© 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. 92929
    Prev
    Next
    INDEX
    Explanations

    XML namespace and schema-instance (xsi)

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

    The neuron fires on numeric tokens (e.g. version numbers or other standalone digits) in code or markup.

    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
    が上が
    -0.91
     Lá
    -0.86
    そのまま
    -0.85
     sirop
    -0.85
    Bung
    -0.83
     succinctly
    -0.82
     törvény
    -0.80
    Lama
    -0.80
    uginosa
    -0.79
    zaron
    -0.77
    POSITIVE LOGITS
    svm
    0.85
    つづく
    0.82
    ']
    0.81
    SearchTree
    0.80
     stb
    0.80
    träglich
    0.79
     الحب
    0.79
     schwierig
    0.79
    logistic
    0.79
     }}$
    0.77
    Activations Density 0.000%

    No Known Activations