© 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. 84090
    Prev
    Next
    INDEX
    Explanations

    containment, attainment, avoidance

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

    This neuron fires on words ending in “-tainment” (e.g. containment, attainment, infotainment).

    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
    of
    -2.97
    是
    -2.72
    發展
    -2.38
    各样的
    -2.33
     '-':
    -2.31
    一旁
    -2.30
    のだが
    -2.30
    儿童
    -2.22
     '\''
    -2.20
    er
    -2.19
    POSITIVE LOGITS
    趼
    3.75
     of
    3.14
    𐄁
    3.00
    ︲
    2.95
    </sup>
    2.77
    </strong>
    2.69
    
    2.63
    汭
    2.56
    ↵
    2.55
     ocas
    2.50
    Activations Density 0.002%

    No Known Activations