© 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. 80685
    Prev
    Next
    INDEX
    Explanations

    Beth followed by names or occupations

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

    The neuron selectively activates on numeric tokens (e.g., years, figures, or other multi‐digit 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_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
     Pressing
    -0.81
     stipulated
    -0.79
    致
    -0.77
    傑
    -0.74
    Inhalt
    -0.74
     Cement
    -0.73
    粋
    -0.73
    ❏
    -0.73
     持ち
    -0.72
    pressing
    -0.72
    POSITIVE LOGITS
    ultor
    0.82
    ',(
    0.82
     ihan
    0.76
     всей
    0.73
    忿
    0.73
     piaci
    0.71
    Conserv
    0.71
    াদ
    0.70
    vente
    0.69
    ^(@
    0.69
    Activations Density 0.126%

    No Known Activations