© 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. 34-GEMMASCOPE-RES-131K
    7. 32706
    Prev
    Next
    INDEX
    Explanations

    contact name or person

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

    This neuron detects terms indicating a point of contact or liaison role (e.g., “point,” “contact,” “liaison,” “person,” “contacts”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     forsk
    -0.75
    бі
    -0.75
    точници
    -0.74
    Morgen
    -0.73
    eksi
    -0.73
    avanje
    -0.72
    casus
    -0.71
    iksi
    -0.71
    vesse
    -0.70
     interdependent
    -0.69
    POSITIVE LOGITS
     contact
    3.55
     contacts
    2.86
    contact
    2.72
     point
    2.70
    Contact
    2.53
     Contact
    2.36
     contacto
    2.30
     Ansprechpartner
    2.30
    CONTACT
    2.17
    contacts
    2.13
    Activations Density 0.028%

    No Known Activations