© 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. 116813
    Prev
    Next
    INDEX
    Explanations

    days of the week or date components

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

    The neuron fires on numeric literals (individual digits and numbers) in code.

    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
    來
    -0.88
     bagno
    -0.85
    vání
    -0.85
     Purg
    -0.85
     النساء
    -0.84
     Castig
    -0.82
     hvilket
    -0.81
     capuche
    -0.80
     universes
    -0.79
    かもし
    -0.79
    POSITIVE LOGITS
    either
    0.89
     либо
    0.85
     either
    0.84
    签到
    0.80
    viewtopic
    0.79
     Sunday
    0.78
     AM
    0.77
     ظهور
    0.77
     Saturday
    0.77
     Monday
    0.76
    Activations Density 0.004%

    No Known Activations