© 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. 34-GEMMASCOPE-RES-131K
    7. 37740
    Prev
    Next
    INDEX
    Explanations

    contact information and personal details

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

    The neuron fires strongly on mentions of personal identifying information fields (e.g. name, address, email, phone number).

    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
     tempore
    -0.91
    ęki
    -0.90
     JSTOR
    -0.89
     Bioaccumulative
    -0.88
    вших
    -0.88
    identity
    -0.87
    în
    -0.84
     hipo
    -0.84
     grands
    -0.83
     donner
    -0.82
    POSITIVE LOGITS
     phone
    1.91
     telephone
    1.72
     email
    1.52
     daytime
    1.41
     phoneNumber
    1.30
     Phone
    1.27
     teléfono
    1.18
    Phone
    1.18
     best
    1.17
     telefoon
    1.16
    Activations Density 0.018%

    No Known Activations