© 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. 36383
    Prev
    Next
    INDEX
    Explanations

    pixel attributes and contexts

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

    The neuron detects occurrences of the substring “pixel” anywhere in the 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
    ↵↵
    -3.75
    比如说
    -2.59
    )$
    -2.59
     完了
    -2.53
    ".
    -2.52
     are
    -2.47
    倘
    -2.45
    但是在
    -2.42
    ↵
    -2.25
    .”
    -2.17
    POSITIVE LOGITS
     Когда
    2.95
    鋦
    2.81
     ڤ
    2.81
    geſ
    2.70
    썽
    2.63
    𓆸
    2.61
    
    2.56
     دانلود
    2.53
    釭
    2.53
    橚
    2.52
    Activations Density 0.010%

    No Known Activations