© 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. 107786
    Prev
    Next
    INDEX
    Explanations

    list manipulation functions

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

    The neuron detects numeric literals (e.g. version numbers or other standalone numbers) 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
    Simp
    -0.96
    সূত্র
    -0.90
     変
    -0.88
     habilitar
    -0.86
     Фу
    -0.86
    reit
    -0.84
    ͹
    -0.83
    Impro
    -0.81
     Madagascar
    -0.80
     Schwier
    -0.80
    POSITIVE LOGITS
     reverse
    1.13
    filter
    1.08
     filter
    1.05
    slice
    1.02
     slice
    1.00
    reverse
    1.00
     join
    1.00
     last
    0.98
     indexOf
    0.94
    sort
    0.91
    Activations Density 0.053%

    No Known Activations