© 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. 7197
    Prev
    Next
    INDEX
    Explanations

    traits and attributes

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

    The neuron fires on programming‐style tokens and numeric literals—i.e. code keywords/identifiers (like “contract,” “uint,” “Zombie”) and numbers or symbols in numeric contexts.

    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
    おき
    -0.84
    ronique
    -0.81
     money
    -0.80
     mone
    -0.79
     arrend
    -0.76
     games
    -0.75
     سیاه
    -0.75
    创建时间
    -0.75
    publisher
    -0.75
    formatDate
    -0.74
    POSITIVE LOGITS
     traits
    1.39
     Traits
    1.27
     trait
    1.21
    Traits
    1.13
     reveal
    1.00
     Trait
    0.99
    traits
    0.97
     attributes
    0.96
     utilidad
    0.91
     Attributes
    0.87
    Activations Density 0.003%

    No Known Activations