© 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. 11633
    Prev
    Next
    INDEX
    Explanations

    wasted time and money

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

    The neuron flags words that convey pointlessness or lack of value—terms like “futile,” “illusory,” and “waste.”

    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
     his
    -1.58
    𓇼
    -1.55
    definitely
    -1.53
     jouent
    -1.44
    apparently
    -1.41
    
    -1.39
    certainly
    -1.38
     -,
    -1.34
     SolutionA
    -1.33
    跸
    -1.31
    POSITIVE LOGITS
    intendo
    1.30
    ⅗
    1.30
    andai
    1.28
     clutter
    1.28
    şil
    1.27
    🫔
    1.25
    
    1.24
     medidor
    1.23
     verur
    1.23
     gewähr
    1.23
    Activations Density 0.029%

    No Known Activations