© 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. 48295
    Prev
    Next
    INDEX
    Explanations

    community organizer, service, transmission

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

    The neuron activates for words and phrases related to "community" and community-based organizations or services.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates strongly on mentions of “community” (including compounds like “community-based”) and related contextual references to community groups.

    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
    になるので
    -1.70
    很赞
    -1.59
    𓁹
    -1.58
    ꙰
    -1.58
    értel
    -1.50
     originalen
    -1.47
    ཿ
    -1.44
     ส์
    -1.43
     grü
    -1.43
    ⍢
    -1.41
    POSITIVE LOGITS
    Doge
    1.64
    「
    1.51
    月から
    1.43
    ционер
    1.41
     and
    1.39
    面的
    1.38
    ercizi
    1.34
    Venez
    1.33
     églises
    1.33
    thâu
    1.31
    Activations Density 0.026%

    No Known Activations