© 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. 14576
    Prev
    Next
    INDEX
    Explanations

    PHP code snippets

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

    This neuron activates on numeric literals in code (e.g. version numbers, integer constants, counts).

    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
    </b>
    -3.19
    </i>
    -2.63
    ”
    -2.56
     ”
    -2.52
     zweite
    -2.47
    -2.39
    s
    -2.39
    ⃢
    -2.36
    嗵
    -2.36
     gemeinsame
    -2.33
    POSITIVE LOGITS
    {
    3.05
    在一个
    2.34
    ه
    2.33
    嵙
    2.23
     Also
    2.20
    在大
    2.20
     scattata
    2.19
     essayé
    2.17
     convencer
    2.17
     According
    2.16
    Activations Density 0.003%

    No Known Activations