© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86338
    Prev
    Next
    INDEX
    Explanations

    phone and telephone

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

    The neuron flags technical references to telephone and telephony systems and devices.

    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
     चीज़
    -1.31
     strona
    -1.30
    箆
    -1.27
    他的
    -1.25
     distribuição
    -1.22
     objectifs
    -1.21
    鳥居
    -1.21
     ―――
    -1.20
     România
    -1.19
     område
    -1.19
    POSITIVE LOGITS
     phone
    1.56
     phones
    1.52
     their
    1.41
     call
    1.39
     voicemail
    1.36
     Phone
    1.35
     number
    1.27
    ☎️
    1.18
    📞
    1.17
     телефона
    1.16
    Activations Density 0.126%

    No Known Activations