© 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. 84310
    Prev
    Next
    INDEX
    Explanations

    shadow and shadows

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

    The neuron is tuned to detect occurrences of the word “shadow” (or its stem) in text.

    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
    榈
    -2.83
    逦
    -2.72
    =’
    -2.36
    ’?
    -2.31
    所有人都
    -2.31
     また
    -2.28
    覿
    -2.28
     auguri
    -2.28
     commenti
    -2.25
     tua
    -2.16
    POSITIVE LOGITS
    趼
    2.50
     of
    2.38
     sech
    2.27
    ⚌
    2.14
     für
    2.14
     diskusi
    2.09
     recompense
    2.08
    罴
    2.03
     häufig
    2.00
    ೢ
    2.00
    Activations Density 0.005%

    No Known Activations