© 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. 45213
    Prev
    Next
    INDEX
    Explanations

    software license text

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

    The neuron fires on numeric strings—integers, decimals, version numbers, years, and similar digit-only tokens.

    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
     forem
    -0.90
    dad
    -0.81
    system
    -0.79
     bom
    -0.79
    count
    -0.79
    SYSTEM
    -0.76
    sal
    -0.73
     how
    -0.73
    number
    -0.72
    mier
    -0.72
    POSITIVE LOGITS
     faixa
    0.81
     imperfectly
    0.79
    );\
    0.78
    harp
    0.76
    isNotNull
    0.76
    IgG
    0.76
    Falcon
    0.75
    睐
    0.75
    underwater
    0.75
     ermöglichen
    0.74
    Activations Density 0.002%

    No Known Activations