© 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. 82530
    Prev
    Next
    INDEX
    Explanations

    using single specific items

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

    The neuron is primarily activated by tokens that are numbers (digit sequences), e.g. version numbers, counts, line numbers, 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
    Ⓒ
    -0.98
     metrics
    -0.88
    founders
    -0.87
     algorit
    -0.86
     cuyo
    -0.85
     others
    -0.83
    érature
    -0.83
     osoby
    -0.82
    UCIÓN
    -0.82
     després
    -0.82
    POSITIVE LOGITS
    separate
    1.09
     terpisah
    0.98
    Today
    0.98
    Separate
    0.98
     modernes
    0.96
     conceito
    0.96
     detachable
    0.95
    Use
    0.94
     használ
    0.91
    Named
    0.90
    Activations Density 0.510%

    No Known Activations