© 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. 34-GEMMASCOPE-RES-131K
    7. 59035
    Prev
    Next
    INDEX
    Explanations

    amino acid sequences

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

    numbers representing measurements or quantities in scientific or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is triggered by numeric tokens (digits or multi-digit numbers) representing counts, measurements, or identifiers in the text.

    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
    ทั้ง
    -0.85
    번
    -0.84
     gmin
    -0.82
    lisis
    -0.82
    lexia
    -0.79
    weif
    -0.79
    ifred
    -0.79
    ưu
    -0.77
    الله
    -0.75
     seized
    -0.74
    POSITIVE LOGITS
    0
    0.94
    情報を
    0.84
    Constructed
    0.82
    ßig
    0.80
     hegemony
    0.79
     helplessness
    0.79
    RECENT
    0.77
    Stuck
    0.77
    金を
    0.76
     tõ
    0.75
    Activations Density 0.153%

    No Known Activations