© 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. 10-GEMMASCOPE-RES-131K
    7. 61274
    Prev
    Next
    INDEX
    Explanations

    solenoid valves or sinusoidal signals

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

    The neuron strongly activates on mentions of electromechanical components—especially “solenoid” (and related terms like solenoid valves).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    y
    -2.50
    艄
    -2.50
     ganzes
    -2.33
     feiner
    -2.28
     kleines
    -2.28
    鷽
    -2.28
    各样的
    -2.23
    𞤢
    -2.20
     him
    -2.17
    
    -2.11
    POSITIVE LOGITS
     WITH
    2.08
    婓
    2.03
    の人生
    2.02
    のは
    1.97
    嵎
    1.97
    adakan
    1.96
    the
    1.88
    𓐍
    1.87
    ｙ
    1.83
    \
    1.80
    Activations Density 0.005%

    No Known Activations