© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66365
    Prev
    Next
    INDEX
    Explanations

    roller coaster rides

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

    The neuron strongly activates on the names of amusement parks and specific ride titles.

    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
    띄
    -0.78
    chability
    -0.74
     Begriffe
    -0.73
     Selanjutnya
    -0.72
     Kegiatan
    -0.71
     captures
    -0.69
    cursos
    -0.69
    setData
    -0.69
    بدو
    -0.69
    子は
    -0.69
    POSITIVE LOGITS
     coaster
    1.35
     coasters
    1.18
     COAST
    0.98
    coaster
    0.98
     Coaster
    0.96
    tamin
    0.95
     wooden
    0.94
     cedar
    0.94
     roller
    0.93
     Busch
    0.92
    Activations Density 0.019%

    No Known Activations