© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25593
    Prev
    Next
    INDEX
    Explanations

    file paths

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

    The neuron activates on numeric tokens (digits or numbers) in mathematical or equation‐like contexts.

    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
     parts
    -0.93
     mitos
    -0.93
     JOptionPane
    -0.91
    ヴァイ
    -0.87
     time
    -0.85
    pearance
    -0.82
     bomba
    -0.80
     adat
    -0.79
     années
    -0.78
    フライ
    -0.78
    POSITIVE LOGITS
    
    0.99
     该
    0.94
     unbelievably
    0.94
     carcinogenic
    0.93
     schuld
    0.92
    ά
    0.90
    anillo
    0.89
     powinna
    0.89
     kostenlosen
    0.88
     jeopardi
    0.88
    Activations Density 0.060%

    No Known Activations