© 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. 106538
    Prev
    Next
    INDEX
    Explanations

    the word "super"

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

    The neuron is detecting occurrences of the keyword “super.”

    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
    Lastname
    -0.90
    volante
    -0.89
    有助
    -0.88
    buon
    -0.85
     prepares
    -0.84
    should
    -0.81
    TEMA
    -0.80
    bjs
    -0.77
    indis
    -0.77
     barbacoa
    -0.76
    POSITIVE LOGITS
    Super
    2.08
     super
    2.03
     Super
    1.77
    SUPER
    1.70
     SUPER
    1.68
     супер
    1.58
    super
    1.57
    スーパー
    1.53
     supers
    1.45
     スーパー
    1.41
    Activations Density 0.016%

    No Known Activations