© 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. 73494
    Prev
    Next
    INDEX
    Explanations

    dial

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

    The neuron is triggered by mentions of dialing or phone‐dial actions, especially when paired with numbers (e.g. “Dial 656,” “dialing,” 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_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
     However
    -3.00
     Currently
    -2.80
     Moreover
    -2.77
     Incidentally
    -2.55
     Даже
    -2.50
     Meanwhile
    -2.47
     Nevertheless
    -2.44
    vantaged
    -2.42
     Therefore
    -2.41
     Additionally
    -2.38
    POSITIVE LOGITS
    ଝ
    2.81
    齪
    2.52
    ༑
    2.52
    
    2.33
    桄
    2.27
    ൎ
    2.25
    锖
    2.25
     på
    2.23
    titial
    2.22
     HAPPENED
    2.22
    Activations Density 0.008%

    No Known Activations