© 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. 10-GEMMASCOPE-RES-131K
    7. 21343
    Prev
    Next
    INDEX
    Explanations

    worth or worthwhile

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

    The neuron fires when it sees the word “worth” (especially in “worth it”) indicating statements or questions about something’s value.

    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
     memutus
    -2.13
     berikan
    -2.05
     menghilangkan
    -1.87
     membag
    -1.87
     memeriksa
    -1.81
    äuser
    -1.76
    uminazione
    -1.75
    wifery
    -1.75
    nisses
    -1.71
     membagikan
    -1.66
    POSITIVE LOGITS
    s
    2.06
    ↵
    2.02
    <em>
    1.88
    </strong>
    1.78
    <strong>
    1.73
    1.69
    "
    1.66
    <sup>
    1.63
     
    1.63
     mentioning
    1.62
    Activations Density 0.011%

    No Known Activations