© 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. 34-GEMMASCOPE-RES-131K
    7. 108837
    Prev
    Next
    INDEX
    Explanations

    food and places

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

    The neuron activates on numeric tokens (years, counts, IDs, or other digit‐based strings).

    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
     утром
    -0.84
     월
    -0.81
     tasty
    -0.81
     vlož
    -0.78
    偏差
    -0.76
     hundreds
    -0.75
    يكل
    -0.74
     museums
    -0.74
     several
    -0.74
     delicious
    -0.73
    POSITIVE LOGITS
     Bookmark
    0.91
    their
    0.91
    他们
    0.90
     casais
    0.86
    acze
    0.84
     rooftop
    0.84
     place
    0.83
    лама
    0.83
    <>();
    0.83
     Operational
    0.83
    Activations Density 0.005%

    No Known Activations