© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74192
    Prev
    Next
    INDEX
    Explanations

    fulfil goals and potential

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

    The neuron consistently spikes on the word “childbirth,” i.e. it detects mentions of childbirth.

    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
    ↵
    -3.14
    酲
    -3.09
     camiset
    -3.00
    珰
    -2.98
     gire
    -2.89
     недавно
    -2.81
    衪
    -2.78
     effets
    -2.75
     火锅
    -2.75
    )’
    -2.67
    POSITIVE LOGITS
     Now
    3.16
    y
    3.13
     quando
    3.02
     {
    2.98
     -
    2.88
     So
    2.83
     Use
    2.83
     You
    2.80
    ".
    2.77
     When
    2.77
    Activations Density 0.010%

    No Known Activations