© 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. 99910
    Prev
    Next
    INDEX
    Explanations

    care

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

    This neuron detects occurrences of the substring “Care” within proper names, titles, or references (e.g. organization or program names).

    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
    ፨
    -3.11
    錞
    -2.86
    紲
    -2.67
    壜
    -2.58
     verminder
    -2.55
     装着
    -2.50
    蚍
    -2.48
    regardless
    -2.47
    쩡
    -2.47
    祤
    -2.45
    POSITIVE LOGITS
    ↵↵
    3.56
    $
    2.92
    :
    2.66
    e
    2.63
    =
    2.55
    i
    2.42
    These
    2.41
    //
    2.38
     .
    2.34
     These
    2.28
    Activations Density 0.006%

    No Known Activations