© 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. 25746
    Prev
    Next
    INDEX
    Explanations

    code placeholders

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

    The neuron fires mainly on numeric literals (numbers and numeric constants) in code examples.

    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
     emblem
    -0.88
    ाइड
    -0.85
    ensitive
    -0.83
    especie
    -0.83
    ական
    -0.82
    indd
    -0.81
    Garmin
    -0.80
    estudi
    -0.80
    喘
    -0.79
    peg
    -0.78
    POSITIVE LOGITS
     you
    1.02
    選択
    0.92
    ukų
    0.84
    //!
    0.84
     aparcamiento
    0.83
     previously
    0.82
     Selecciona
    0.81
     defraud
    0.81
    りましたが
    0.80
     dragen
    0.79
    Activations Density 0.017%

    No Known Activations