© 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. 103309
    Prev
    Next
    INDEX
    Explanations

    cast aluminum, wheels, metal, & crew

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

    The neuron consistently fires on the standalone word “Cast” regardless of context.

    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
     ordinaria
    -0.91
     calo
    -0.83
     pertanto
    -0.80
    ček
    -0.79
    Crack
    -0.79
    GREES
    -0.79
    ाइट
    -0.79
     compil
    -0.79
    CultureInfo
    -0.78
    <0xB9>
    -0.77
    POSITIVE LOGITS
     Cast
    1.80
     cast
    1.57
    Cast
    1.41
     Casting
    1.34
     casting
    1.30
    Casting
    1.24
     CAST
    1.20
     asper
    1.20
     adrift
    1.20
    cast
    1.18
    Activations Density 0.029%

    No Known Activations