© 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. 10-GEMMASCOPE-RES-131K
    7. 44144
    Prev
    Next
    INDEX
    Explanations

    locations and addresses

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

    The neuron activates on numeric tokens and digit sequences (e.g. addresses, phone numbers, or other 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_10/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
     alguém
    -1.33
     völ
    -1.30
     важ
    -1.29
    
    -1.29
     are
    -1.29
    чну
    -1.29
    זיה
    -1.25
     say
    -1.23
     eventuali
    -1.23
    levé
    -1.23
    POSITIVE LOGITS
     biß
    1.59
     
    1.55
     aislada
    1.48
     другим
    1.40
    一个小
    1.35
     to
    1.34
     srdce
    1.31
     framför
    1.31
     красный
    1.30
     verdaderos
    1.27
    Activations Density 0.269%

    No Known Activations