© 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. 22-GEMMASCOPE-RES-131K
    7. 39606
    Prev
    Next
    INDEX
    Explanations

    hardware connectors and fasteners

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

    The neuron detects technical mentions of connectors or coupling components (e.g. cables, connectors, couplings) used to join devices or structures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     
    -1.15
     there
    -1.12
    ഖ
    -1.11
    ,
    -1.05
     cubrir
    -1.05
    boolean
    -1.01
     hornear
    -1.00
    f
    -0.99
    もちろん
    -0.99
    Geschiedenis
    -0.98
    POSITIVE LOGITS
     recommandée
    1.41
    ֩
    1.40
     citoy
    1.30
     chrétien
    1.21
    jmu
    1.18
    юль
    1.15
     zapatillas
    1.14
     сахара
    1.13
    ଼
    1.13
    〕
    1.12
    Activations Density 0.071%

    No Known Activations