© 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. 116007
    Prev
    Next
    INDEX
    Explanations

    Muse, Musa, Moise, Musetta

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

    The neuron strongly activates on tokens beginning with the sequence “Mus” (and very close variants, e.g. Muse, Musa, Museo, Musetta, 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_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
    REMARKS
    -0.76
    naden
    -0.76
     kapturem
    -0.71
    FOLLOW
    -0.70
     prensa
    -0.69
    hacia
    -0.69
    cursos
    -0.68
    żdż
    -0.68
     Yü
    -0.68
    动作
    -0.68
    POSITIVE LOGITS
    veni
    0.90
    triangleright
    0.84
    Score
    0.81
    Watson
    0.81
     Muse
    0.77
     charged
    0.77
    footnote
    0.77
    WT
    0.75
     Watson
    0.75
    vato
    0.71
    Activations Density 0.014%

    No Known Activations