© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 49905
    Prev
    Next
    INDEX
    Explanations

    csrf token or session put

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

    The neuron fires strongly on numeric tokens and numerical expressions (e.g. standalone digits, ranges, and percentages).

    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
    Hash
    -0.90
    Auth
    -0.86
     Schema
    -0.85
    Cache
    -0.84
    Schema
    -0.83
    lando
    -0.81
    Session
    -0.77
    DB
    -0.77
     Auth
    -0.77
    Route
    -0.77
    POSITIVE LOGITS
    Prez
    0.75
     raged
    0.74
    EOS
    0.70
     SetUp
    0.69
     clings
    0.69
    ontroller
    0.68
    TOKEN
    0.68
     deterioration
    0.67
     token
    0.66
     setColor
    0.65
    Activations Density 0.066%

    No Known Activations