© 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. 103966
    Prev
    Next
    INDEX
    Explanations

    good and evil

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

    The neuron specifically detects occurrences of the word “good.”

    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
     kupa
    -1.55
    小伙伴
    -1.39
     Ukraina
    -1.36
     ſame
    -1.36
     makam
    -1.35
     begon
    -1.34
     konsult
    -1.34
     Diſ
    -1.33
     onderdelen
    -1.32
    ть
    -1.31
    POSITIVE LOGITS
     спеціаль
    1.54
     has
    1.48
     Veränderung
    1.47
     яку
    1.44
     she
    1.42
    زوج
    1.41
     rzeczy
    1.40
    或者
    1.39
     merece
    1.36
    Those
    1.33
    Activations Density 0.015%

    No Known Activations