© 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. 70931
    Prev
    Next
    INDEX
    Explanations

    the early life

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

    The neuron detects document section headings (e.g. “Early life and education,” “History,” “Career,” 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
     startet
    -1.69
    ra
    -1.63
     dring
    -1.62
    攆
    -1.54
     wirk
    -1.51
    -
    -1.49
     à
    -1.48
     propone
    -1.48
    立马
    -1.47
    üge
    -1.45
    POSITIVE LOGITS
    vantaged
    2.00
    spricht
    1.86
     voegen
    1.73
     only
    1.72
    quirrels
    1.68
    oustics
    1.66
    ouflage
    1.65
    apkan
    1.62
     leftovers
    1.62
    ifoli
    1.61
    Activations Density 0.005%

    No Known Activations