© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115615
    Prev
    Next
    INDEX
    Explanations

    seven followed by specific words

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

    The neuron is activated by numeric tokens or number‐related words (digits, years, ordinals, etc.).

    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
    zkou
    -0.84
     recruited
    -0.81
    mannen
    -0.75
    uction
    -0.74
    celery
    -0.73
     spe
    -0.73
     bruge
    -0.72
    匕
    -0.72
    pumpkin
    -0.72
     vorg
    -0.71
    POSITIVE LOGITS
    而不是
    0.85
    ᶠ
    0.82
     七
    0.81
    ENSES
    0.77
     sieben
    0.77
     этого
    0.74
     SEVEN
    0.74
     leaft
    0.73
    ♗
    0.73
    更是
    0.72
    Activations Density 0.036%

    No Known Activations