© 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. 22-GEMMASCOPE-RES-131K
    7. 68770
    Prev
    Next
    INDEX
    Explanations

    selection and order actions

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

    The neuron fires on direct call-to-action imperatives (e.g. “Click HERE,” “choose your options,” “make your selection”) in marketing or e-commerce copy.

    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
     their
    -1.13
    Existe
    -1.13
    Distancia
    -1.11
    drawSprites
    -1.11
    ouncer
    -1.09
     کره
    -1.09
    :
    -1.09
     started
    -1.09
    ष्
    -1.05
    ScreenState
    -1.05
    POSITIVE LOGITS
     الجلد
    1.22
    のだろう
    1.22
     øns
    1.17
    𝑈
    1.17
     you
    1.16
     også
    1.15
    ellement
    1.13
     aunque
    1.12
     dimanche
    1.08
     ویتامین
    1.08
    Activations Density 0.032%

    No Known Activations