© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47745
    Prev
    Next
    INDEX
    Explanations

    cloud service configuration

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

    The neuron fires strongly on numeric literals—especially floating-point numbers appearing in text or 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_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
     Pfar
    -1.59
     katholischen
    -1.55
    摂取
    -1.55
    ⼿
    -1.50
    ֺ
    -1.49
    研究生
    -1.47
     Stadtteil
    -1.46
     وصلة
    -1.42
     Öffnungszeiten
    -1.40
    requently
    -1.39
    POSITIVE LOGITS
    ῤ
    1.66
     besonder
    1.63
    ּוֹ
    1.59
     your
    1.59
    𓂂
    1.53
    וּ
    1.52
    靭
    1.49
    ınıza
    1.49
    𓏸
    1.48
    🪛
    1.48
    Activations Density 0.867%

    No Known Activations