© 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. 74019
    Prev
    Next
    INDEX
    Explanations

    politicians and leaders

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

    This neuron primarily activates on personal names and titles, highlighting mentions of people (proper names and their roles).

    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
    m
    -1.53
    h
    -1.52
    w
    -1.45
    e
    -1.45
     '
    -1.41
    de
    -1.38
    v
    -1.37
     
    -1.35
    f
    -1.35
     инструментов
    -1.32
    POSITIVE LOGITS
    thargy
    1.57
    𓋼
    1.57
    blins
    1.57
     vormen
    1.53
    畎
    1.47
     迷你
    1.45
    pholes
    1.43
    刧
    1.42
    bbero
    1.41
    cún
    1.41
    Activations Density 0.007%

    No Known Activations