© 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. 22-GEMMASCOPE-RES-131K
    4. 13609
    Prev
    Next
    INDEX
    Explanations

    social change, community, leaders, potential

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

    The neuron fires on language describing an organization’s mission or purpose—i.e. positive, impact-oriented words (empowering, supporting, navigating, helping, creating, fulfilling potential, etc.) that articulate goals and benefits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     if
    -1.19
     their
    -1.13
     staff
    -1.13
     now
    -1.13
     that
    -1.13
     routinely
    -1.11
    讳
    -1.11
     or
    -1.11
     presumably
    -1.09
     September
    -1.09
    POSITIVE LOGITS
     アクリル
    1.27
     создавать
    1.26
     trám
    1.25
    ፲
    1.24
    çim
    1.23
    🪤
    1.23
     gegenwär
    1.22
    ects
    1.17
    ckeye
    1.16
    ifiable
    1.13
    Activations Density 0.094%

    No Known Activations