© 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. 10-GEMMASCOPE-RES-131K
    7. 66959
    Prev
    Next
    INDEX
    Explanations

    hip hop

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

    The neuron responds to occurrences of the term “hip,” especially where it appears as part of “hip-hop” or shorthand for being trendy.

    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
    ↵
    -1.83
    M
    -1.63
    E
    -1.60
     schnelle
    -1.44
     s
    -1.41
     distinguishing
    -1.35
    N
    -1.33
     heirloom
    -1.31
    \
    -1.29
     rema
    -1.27
    POSITIVE LOGITS
     bambu
    1.73
     plastico
    1.63
    ܞ
    1.62
     catalogo
    1.60
     esat
    1.52
    嶸
    1.50
     sepak
    1.49
     viera
    1.48
     muka
    1.47
    犸
    1.46
    Activations Density 0.034%

    No Known Activations