© 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. 59192
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and code

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

    The main thing this neuron does is detect the word “cases,” as used in LaTeX or code environments.

    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
    HostException
    -2.17
    tifiable
    -2.11
     SPRINGS
    -2.05
    ፪
    -2.03
    你在
    -2.03
    žní
    -2.02
     ผ้า
    -2.02
    ꈊ
    -1.98
    ophageal
    -1.97
    米的
    -1.96
    POSITIVE LOGITS
     From
    2.27
    </strong>
    2.14
    ’
    2.03
    -
    2.02
    ↵
    1.88
     Также
    1.86
     Очень
    1.83
    </em>
    1.81
     Хотя
    1.80
    _
    1.78
    Activations Density 0.000%

    No Known Activations