© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38711
    Prev
    Next
    INDEX
    Explanations

    cookies to

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

    The neuron fires on cookie-policy language, especially the word “cookies” and related site consent phrasing.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     erscheinen
    -1.50
    y
    -1.48
     its
    -1.41
    before
    -1.41
    訁
    -1.34
     adaptarse
    -1.33
     już
    -1.31
    了很多
    -1.27
    和大
    -1.26
    type
    -1.25
    POSITIVE LOGITS
    __('
    1.55
    ellä
    1.41
    рования
    1.40
    </tfoot>
    1.39
    <td>
    1.38
     adresse
    1.34
    걍
    1.32
    嗞
    1.30
    glVertex
    1.30
    ных
    1.30
    Activations Density 0.564%

    No Known Activations