© 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. 23951
    Prev
    Next
    INDEX
    Explanations

    system operation and functioning

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

    The neuron fires on terms describing a system or process’s operation or proper functioning.

    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
    蜮
    -1.54
    izes
    -1.45
    ҿ
    -1.44
    </b>
    -1.40
    |}{}
    -1.40
    árias
    -1.39
    媲
    -1.38
     οπο
    -1.37
    ists
    -1.36
    ScopeManager
    -1.35
    POSITIVE LOGITS
    j
    1.68
    N
    1.37
    x
    1.34
    鰾
    1.31
     soo
    1.30
    V
    1.28
    com
    1.27
    ၟ
    1.26
    椎
    1.26
     создания
    1.23
    Activations Density 0.040%

    No Known Activations