© 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. 34-GEMMASCOPE-RES-131K
    7. 4223
    Prev
    Next
    INDEX
    Explanations

    cult movies, cult classics, cult leader

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

    This neuron detects occurrences of the substring “cult” (e.g. in “Cult,” “cultured,” “cult classic,” etc.).

    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
    웹
    -0.90
    wnątrz
    -0.89
     couvre
    -0.89
    落ちる
    -0.85
     Effects
    -0.84
    buquerque
    -0.83
    ','',
    -0.82
    撂
    -0.82
    گران
    -0.81
    𝓐
    -0.81
    POSITIVE LOGITS
     cult
    2.78
     Cult
    2.39
    cult
    2.22
    Cult
    2.16
     куль
    1.73
     CULT
    1.73
     Kult
    1.60
     cults
    1.59
     kult
    1.51
     culto
    1.51
    Activations Density 0.011%

    No Known Activations