© 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. 73302
    Prev
    Next
    INDEX
    Explanations

    usercontent links and questions

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

    The neuron is picking up host/domain name tokens in URLs (e.g. “usercontent,” “cdn,” etc.).

    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
    Here
    -2.59
    section
    -2.31
    To
    -2.28
     большим
    -2.23
    Only
    -2.16
    情報を
    -2.16
    At
    -2.11
    不会
    -2.09
    only
    -2.05
     Antrags
    -1.98
    POSITIVE LOGITS
     of
    3.02
    '
    2.66
    ⑊
    2.48
    弍
    2.44
    趼
    2.17
    醯
    2.16
    歺
    2.09
    ſu
    1.98
    疴
    1.97
    总会
    1.96
    Activations Density 0.000%

    No Known Activations