© 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. 100562
    Prev
    Next
    INDEX
    Explanations

    Ing words

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

    The neuron is highly sensitive to the three-letter capitalized sequence “Ing” (i.e. words beginning with “Ing”).

    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
    0
    -4.38
    約
    -3.28
    Ideally
    -3.27
    1
    -3.23
    </strong>
    -3.06
    Perhaps
    -3.06
    It
    -3.03
    </h3>
    -3.03
    Regardless
    -3.03
    When
    -3.02
    POSITIVE LOGITS
    s
    3.11
    倌
    2.86
    🧌
    2.84
    τές
    2.77
    鑁
    2.69
    諏
    2.69
    ѣмъ
    2.56
    玙
    2.56
    اتها
    2.55
    沩
    2.55
    Activations Density 0.004%

    No Known Activations