© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40420
    Prev
    Next
    INDEX
    Explanations

    interventions

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

    The neuron primarily fires on occurrences of the word “intervention” (including its plural form “interventions”).

    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
    '
    -2.84
    href
    -2.28
    穑
    -2.09
    €™
    -2.08
    价格
    -2.03
     adaptable
    -1.98
    眼睛
    -1.95
    jdons
    -1.95
     gruppe
    -1.95
    厯
    -1.95
    POSITIVE LOGITS
     alemán
    2.45
    他也
    2.33
     Для
    2.22
    站起来
    2.19
     После
    2.17
     Popis
    2.14
    ❉
    2.11
    摃
    2.08
    </em>
    2.08
     Při
    2.06
    Activations Density 0.012%

    No Known Activations