© 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. 85573
    Prev
    Next
    INDEX
    Explanations

    sequestration

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

    The neuron detects the term "sequestration" and related forms of the word in scientific and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on occurrences of the word root “sequestr–,” i.e. terms relating to sequestration.

    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
     assistente
    -2.58
     sorriso
    -2.52
    5
    -2.45
    4
    -2.41
    颪
    -2.27
     concorda
    -2.25
     :
    -2.23
     Cár
    -2.23
    也在
    -2.22
     متوسط
    -2.22
    POSITIVE LOGITS
    哔
    2.28
    medriver
    2.17
    しちゃ
    2.14
    ᐡ
    2.14
    婚礼
    2.14
    ła
    2.13
    cookieParser
    2.08
    ቍ
    2.06
    𖥦
    2.06
    ญี่ป
    2.02
    Activations Density 0.008%

    No Known Activations