© 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. 22-GEMMASCOPE-RES-131K
    7. 15840
    Prev
    Next
    INDEX
    Explanations

    proper names and compound technical terms

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

    The neuron detects numeric constants (integer literals) within code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ét
    -1.09
    佷
    -1.09
     my
    -1.08
    本作
    -1.06
    плення
    -1.05
    喩
    -1.05
     négoci
    -1.05
     negar
    -1.04
    EDOM
    -1.03
     nadar
    -1.03
    POSITIVE LOGITS
    rrbracket
    1.09
    ntry
    1.02
     чтобы
    1.00
     to
    0.96
    Карьера
    0.95
    摂取
    0.94
    savevideo
    0.94
     Belakang
    0.91
    </strong>
    0.90
     //
    0.90
    Activations Density 0.001%

    No Known Activations