© 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. 97998
    Prev
    Next
    INDEX
    Explanations

    use of cookies

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

    The neuron fires on cookie‐consent or cookie‐policy language—i.e. mentions of “cookies” (and nearby words like “use,” “of,” etc.) in website privacy notices.

    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
    禽
    -0.83
     tabletop
    -0.81
    Ibu
    -0.80
     военно
    -0.77
    陂
    -0.77
    RIN
    -0.75
    SPECIES
    -0.74
    ENSUS
    -0.73
     deliverables
    -0.72
    Feet
    -0.72
    POSITIVE LOGITS
     cookies
    5.56
     cookie
    4.88
     Cookies
    4.41
    cookie
    4.28
    cookies
    4.22
    Cookie
    4.03
    Cookies
    3.98
     Cookie
    3.95
    COOKIE
    3.25
     COOKIE
    3.14
    Activations Density 0.100%

    No Known Activations