© 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. 78361
    Prev
    Next
    INDEX
    Explanations

    code and html snippets

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

    The neuron activates on standalone numeric tokens (numbers) in the text.

    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
     even
    -1.09
     mesmo
    -0.98
    げた
    -0.95
     including
    -0.94
     according
    -0.93
    忖
    -0.93
     même
    -0.92
     like
    -0.92
    ")){
    -0.91
    柿
    -0.89
    POSITIVE LOGITS
    ɵɵelementEnd
    1.14
    Какой
    0.96
     volledig
    0.94
     conquering
    0.92
     gezegd
    0.90
     modelleri
    0.88
     fearful
    0.88
    凄い
    0.86
    Код
    0.86
    fertigung
    0.85
    Activations Density 0.038%

    No Known Activations