© 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. 83694
    Prev
    Next
    INDEX
    Explanations

    javascript code and english phrases

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

    The neuron primarily lights up on numeric literals (number tokens) 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
     outros
    -0.79
    охо
    -0.76
     paraíso
    -0.75
    梦见
    -0.73
    ★★★
    -0.73
     limitée
    -0.73
    CARL
    -0.73
    Giveaway
    -0.71
     például
    -0.71
    中です
    -0.71
    POSITIVE LOGITS
     khỏe
    0.84
    PLACEMENT
    0.84
     uživ
    0.78
    regas
    0.77
    Sejarah
    0.77
     Endgame
    0.76
    mmation
    0.76
    gtr
    0.74
    ammen
    0.74
    INCREMENT
    0.74
    Activations Density 0.011%

    No Known Activations