© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25826
    Prev
    Next
    INDEX
    Explanations

    component components component-based

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

    This neuron fires on code identifiers or comments containing the word “Component” (e.g. “COMPONENT_NAME,” “component,” etc.).

    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
    of
    -2.95
    梛
    -2.50
    ti
    -2.47
    孩子
    -2.38
     они
    -2.34
     technologically
    -2.34
     glimpse
    -2.33
    out
    -2.30
    畀
    -2.28
    一個
    -2.25
    POSITIVE LOGITS
    ですので
    2.78
    というわけで
    2.73
    昻
    2.70
    赑
    2.70
    𖥧
    2.61
    玕
    2.47
    ୈ
    2.42
     और
    2.41
    鲩
    2.41
    𝟭
    2.39
    Activations Density 0.028%

    No Known Activations