© 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. 8290
    Prev
    Next
    INDEX
    Explanations

    IP protection and degrees

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

    The neuron activates on technical specification details—particularly numeric values, units, and industrial ratings (e.g. “IP65,” fanless, temperature ranges).

    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
     následu
    -0.71
     Warning
    -0.69
    Google
    -0.68
     запуска
    -0.65
    warning
    -0.65
    aquarium
    -0.63
    斗
    -0.63
    Warning
    -0.63
    oprene
    -0.62
    牡蠣
    -0.61
    POSITIVE LOGITS
     protection
    1.37
     Protection
    1.19
     IP
    1.16
     protected
    1.15
     IK
    1.13
     degree
    1.08
     degrees
    1.03
    防护
    1.03
     Degrees
    1.00
    Protection
    0.96
    Activations Density 0.018%

    No Known Activations