© 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. 22-GEMMASCOPE-RES-131K
    7. 27480
    Prev
    Next
    INDEX
    Explanations

    contact via email or phone

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

    The neuron flags instances where the text gives contact instructions—especially phrases like “email us,” “contact us,” or “call by phone.”

    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
    Kontrola
    -1.13
    ハンドメイド
    -1.05
    qxd
    -1.05
     برخی
    -1.03
    重大
    -1.03
    Przeczytaj
    -1.02
    也要
    -1.00
     churrasco
    -0.98
     tava
    -0.98
     Akku
    -0.97
    POSITIVE LOGITS
     either
    1.91
     or
    1.51
     либо
    1.47
    either
    1.34
     through
    1.30
     via
    1.27
     at
    1.22
     email
    1.20
     any
    1.16
     contact
    1.15
    Activations Density 0.017%

    No Known Activations