© 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. 40731
    Prev
    Next
    INDEX
    Explanations

    test cases or test plans

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

    The neuron fires on occurrences of “test” and its morphological variants (e.g. “testing,” “test case,” “Test Plan,” etc.), i.e. it detects references to testing activities or artifacts.

    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
    </h2>
    -1.36
     vanske
    -1.32
    '
    -1.31
     about
    -1.30
    ？】
    -1.26
     to
    -1.24
     constituye
    -1.22
    キッド
    -1.19
     sikkert
    -1.18
    ？』
    -1.18
    POSITIVE LOGITS
    also
    1.49
    らせる
    1.42
     también
    1.42
    らせて
    1.38
    ─
    1.37
    ⸗
    1.30
    gelegen
    1.28
     opinión
    1.27
     crise
    1.27
    ACIÓN
    1.26
    Activations Density 0.098%

    No Known Activations