© 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. 22-GEMMASCOPE-RES-131K
    7. 38382
    Prev
    Next
    INDEX
    Explanations

    forum signatures dates and urls

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

    This neuron fires on tokens containing digits (e.g. times, post counts, IDs, URLs with 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_22/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
    ||}
    -0.92
    greenrobot
    -0.90
     
    -0.87
    zczy
    -0.85
    чения
    -0.85
    皝
    -0.84
    ня
    -0.83
    chandra
    -0.82
     frambo
    -0.82
    owaniem
    -0.82
    POSITIVE LOGITS
    辯
    1.13
    Zü
    1.05
     metav
    1.05
     but
    1.00
     ottim
    0.99
    淪
    0.98
    踝
    0.94
    社區
    0.94
     apparten
    0.93
    quar
    0.92
    Activations Density 0.017%

    No Known Activations