© 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. 34-GEMMASCOPE-RES-131K
    7. 62857
    Prev
    Next
    INDEX
    Explanations

    common good

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

    The neuron detects occurrences of “good” (and its modifiers) in idiomatic contexts expressing benefit or 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_34/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
     unters
    -0.77
    middelen
    -0.75
    ֢
    -0.75
    babu
    -0.73
    െ
    -0.73
    lorin
    -0.73
    substack
    -0.71
    オススメです
    -0.71
     secundario
    -0.70
    おすすめです
    -0.69
    POSITIVE LOGITS
     good
    5.00
    good
    3.63
    Good
    3.25
     Good
    2.97
     GOOD
    2.91
    GOOD
    2.77
     buenas
    2.03
     buena
    2.00
     goods
    1.99
     goede
    1.85
    Activations Density 0.026%

    No Known Activations