© 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. 12646
    Prev
    Next
    INDEX
    Explanations

    worry about things

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

    The neuron activates on occurrences of the word “worry” (including its inflected form “worrying”).

    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
    acterísticas
    -3.28
    퐿
    -2.69
    I
    -2.64
    怱
    -2.58
    蠵
    -2.56
    玊
    -2.55
     allegedly
    -2.52
    🫓
    -2.50
    噚
    -2.50
    }$.
    -2.48
    POSITIVE LOGITS
    ↵↵
    2.88
    .
    2.75
    d
    2.48
     I
    2.42
     что
    2.25
      
    2.17
    the
    2.09
    ating
    2.08
    <i>
    2.06
    able
    2.05
    Activations Density 0.005%

    No Known Activations