© 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. 22258
    Prev
    Next
    INDEX
    Explanations

    inexpensive

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

    The neuron fires on words that signal low cost, especially the adjective “inexpensive.”

    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
    ೣ
    -2.63
     renowned
    -2.39
     lament
    -2.28
     ilumina
    -2.27
    AdvEx
    -2.25
    ዣ
    -2.20
     magnificent
    -2.16
    寕
    -2.14
    秾
    -2.14
     pérd
    -2.14
    POSITIVE LOGITS
    vantaged
    3.02
    翾
    2.64
    酲
    2.53
    ја
    2.41
     него
    2.23
    ist
    2.16
     можете
    2.13
    ى
    2.09
     години
    2.08
    вого
    2.06
    Activations Density 0.004%

    No Known Activations