© 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. 22-GEMMASCOPE-RES-131K
    4. 36101
    Prev
    Next
    INDEX
    Explanations

    website cookies

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

    The main thing this neuron does is detect mentions of “cookie” or “cookies” in website/privacy contexts.

    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
     of
    -1.37
     using
    -1.27
     out
    -1.14
     \
    -1.13
     he
    -1.06
     используя
    -1.04
     USING
    -1.03
     með
    -1.03
    GLfloat
    -1.02
    ([
    
    -1.02
    POSITIVE LOGITS
    ਫ਼
    1.46
     різних
    1.19
     饼
    1.16
     siinä
    1.11
    espół
    1.10
    QUESTIONS
    1.10
     corações
    1.09
    biť
    1.09
     وغير
    1.09
    mahami
    1.09
    Activations Density 0.024%

    No Known Activations