© 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. 48953
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    The neuron activates on numeric tokens—i.e. strings of digits (numbers) rather than words.

    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
    屋さん
    -1.02
    うら
    -1.01
    responsibility
    -0.99
    Then
    -0.96
     letzt
    -0.94
    IORITY
    -0.93
    ご了承ください
    -0.93
    ౦
    -0.93
    never
    -0.92
    スポンサーリンク
    -0.92
    POSITIVE LOGITS
    ผ้า
    0.97
    <td>
    0.96
    Kontrola
    0.94
    );
    0.85
    PyTuple
    0.84
    Crypto
    0.84
    Bernard
    0.82
    ());
    0.82
    жат
    0.82
     nepiecieš
    0.82
    Activations Density 0.111%

    No Known Activations