© 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. 22-GEMMASCOPE-RES-131K
    7. 27110
    Prev
    Next
    INDEX
    Explanations

    earned trust and customers

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

    The neuron detects occurrences of the root “earn” (e.g. earn, earned, earning).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ي
    -2.56
    蜩
    -2.25
    หรือ
    -2.25
    และ
    -2.19
    ⢊
    -2.16
    ᠂
    -2.14
    бурге
    -2.09
    ਃ
    -2.08
    最后由
    -1.98
    罍
    -1.96
    POSITIVE LOGITS
    ↵↵
    2.69
    "
    2.38
    {
    2.23
    .")
    2.14
     verbess
    1.99
    旆
    1.97
     メニュー
    1.96
     biß
    1.95
    $
    1.90
    ᗪ
    1.86
    Activations Density 0.012%

    No Known Activations