© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58643
    Prev
    Next
    INDEX
    Explanations

    research study and legal opinion

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

    This neuron primarily responds to tokens containing digits—e.g. numeric values, hex or percent-encoded sequences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     الرسم
    -0.86
    Ced
    -0.79
    SME
    -0.77
     systé
    -0.75
    🧼
    -0.75
    lagi
    -0.74
    🕕
    -0.74
    piration
    -0.73
     līdz
    -0.73
     Relating
    -0.73
    POSITIVE LOGITS
     study
    1.09
    研究
    1.02
     glorious
    0.99
     studies
    0.99
     researchers
    0.95
     research
    0.91
     연구
    0.90
     vescovo
    0.85
     modern
    0.85
    المراجع
    0.85
    Activations Density 0.006%

    No Known Activations