© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90520
    Prev
    Next
    INDEX
    Explanations

    digits and identifiers

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

    The neuron responds to sequences of digits (numeric identifiers, page/case numbers, citation markers, etc.).

    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
     zä
    -1.05
    月号
    -1.03
     esbo
    -0.98
     subterrá
    -0.96
     their
    -0.95
     beschreibt
    -0.94
     miesięcy
    -0.92
    берите
    -0.91
     jedynie
    -0.91
    meau
    -0.90
    POSITIVE LOGITS
    zenio
    0.94
     contratto
    0.90
     Bescheid
    0.87
    ...\
    0.85
    imal
    0.85
    Waktu
    0.84
     rester
    0.83
     Uang
    0.82
     Biaya
    0.82
     Terima
    0.82
    Activations Density 0.006%

    No Known Activations