© 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. 118061
    Prev
    Next
    INDEX
    Explanations

    free, price, countdown, translation

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

    The neuron flags promotional or call-to-action terms that advertise content availability (e.g. “free,” “download,” “movie,” “next,” “air,” “format”).

    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
    мой
    -0.90
     februari
    -0.82
     marcha
    -0.79
     operar
    -0.77
     rí
    -0.77
     ambiente
    -0.75
    igneurs
    -0.75
    topRight
    -0.74
     delar
    -0.73
     ymax
    -0.73
    POSITIVE LOGITS
     estimated
    1.02
     also
    1.01
     income
    0.99
    INCLUDING
    0.88
    dado
    0.86
     net
    0.85
     earnings
    0.85
     reforzar
    0.84
     także
    0.84
    tituto
    0.83
    Activations Density 0.006%

    No Known Activations