© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92947
    Prev
    Next
    INDEX
    Explanations

    patented gadgets and technology

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

    This neuron detects product marketing copy that states a product’s purpose/primary benefit and intended user (e.g., short benefit/“helps X do Y”) .

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cairo
    0.41
    Volatility
    0.39
    Search
    0.39
     oversee
    0.39
    Capabilities
    0.38
     overseeing
    0.38
     breadth
    0.38
    缀
    0.38
     তারই
    0.37
    List
    0.37
    POSITIVE LOGITS
     patented
    1.01
     inventors
    0.69
     kits
    0.68
    ®.
    0.67
     patente
    0.67
    ®
    0.67
     revolucion
    0.64
    ®,
    0.64
    ™.
    0.64
     gadget
    0.63
    Activations Density 0.077%

    No Known Activations