© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34719
    Prev
    Next
    INDEX
    Explanations

    contact us or details

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

    The neuron fires on contact‐information blocks—headers like “Contact,” “contact us,” email/phone labels, and phone‐number digits.

    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
    Spenden
    -1.07
    Übernach
    -1.00
    Sicherheit
    -0.99
    Öffnungszeiten
    -0.93
    Qualität
    -0.89
    Therapie
    -0.84
    gebühr
    -0.84
    Angebot
    -0.81
    Pflege
    -0.80
    Arbeits
    -0.79
    POSITIVE LOGITS
     your
    0.97
     Öz
    0.92
     dazed
    0.89
    洗浄
    0.87
    Причины
    0.86
     mottled
    0.84
     customer
    0.83
     competent
    0.82
     Empfindung
    0.79
     TÜV
    0.78
    Activations Density 0.025%

    No Known Activations