© 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. 84621
    Prev
    Next
    INDEX
    Explanations

    changing text case

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

    The neuron activates on code tokens that invoke lowercasing (or similar text-normalization) methods.

    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
    </h5>
    -1.93
    </h3>
    -1.90
    ⃨
    -1.69
     antes
    -1.69
     preocup
    -1.64
    </u>
    -1.63
     The
    -1.62
     doctrina
    -1.60
     programa
    -1.59
     justo
    -1.59
    POSITIVE LOGITS
    9
    2.89
    6
    2.86
    7
    2.45
    2
    2.44
    8
    2.41
    3
    2.39
    4
    2.39
    5
    2.20
    after
    2.14
    only
    1.84
    Activations Density 0.004%

    No Known Activations