© 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. 21738
    Prev
    Next
    INDEX
    Explanations

    activities and education

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

    The neuron is especially responsive to words naming personal pursuits or skills—like arts and crafts, musical instruments, sports, and other hobbies.

    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
     that
    -2.34
    nitř
    -1.55
     enmar
    -1.46
     increíbles
    -1.41
     asmen
    -1.38
    }")]
    -1.36
     verksamhet
    -1.35
     begle
    -1.34
     fordert
    -1.34
     its
    -1.33
    POSITIVE LOGITS
     and
    2.58
     навіть
    1.39
     даже
    1.32
    spania
    1.25
    Meld
    1.24
    urcht
    1.24
    IPPI
    1.23
     السياسة
    1.22
     anny
    1.21
    Ered
    1.21
    Activations Density 0.079%

    No Known Activations