© 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. 10-GEMMASCOPE-RES-131K
    7. 21642
    Prev
    Next
    INDEX
    Explanations

    telephone number

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

    The neuron activates on telephone‐related references, i.e. labels and sequences indicating phone contact information.

    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
    笮
    -2.94
    鼱
    -2.81
     veren
    -2.55
    寕
    -2.45
    s
    -2.27
    '
    -2.22
    </b>
    -2.22
    y
    -2.14
     leur
    -2.03
    屨
    -2.00
    POSITIVE LOGITS
     Bereichen
    2.66
     Eigentü
    2.52
     praktischen
    2.47
     męskie
    2.42
    
    2.41
    珢
    2.41
     Mitteln
    2.38
     vollständ
    2.38
     erfolgreichen
    2.38
    </h3>
    2.34
    Activations Density 0.012%

    No Known Activations