© 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. 10-GEMMASCOPE-RES-131K
    4. 65197
    Prev
    Next
    INDEX
    Explanations

    hip-hop

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

    This neuron fires on mentions of the term “hip hop” (including variations like “Hip-Hop,” “hip hop,” 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_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
    '
    -2.42
     {
    -2.30
    1
    -2.28
    ).
    -2.27
    ),
    -2.23
    *.
    -2.20
    *:
    -2.05
    â
    -2.05
    The
    -2.02
    ();
    -1.99
    POSITIVE LOGITS
    溷
    2.03
    zelfde
    2.00
     minggu
    1.96
    ewear
    1.94
     Agrega
    1.89
    chläge
    1.87
     wedstrijd
    1.87
     renaissance
    1.86
    ugeot
    1.86
    heiros
    1.82
    Activations Density 0.005%

    No Known Activations