© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48640
    Prev
    Next
    INDEX
    Explanations

    community, support, together

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

    The neuron activates on words and phrases conveying collective group participation or togetherness (e.g. community, we, together, fellowship).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ويكيپيديا
    -0.84
    Participation
    -0.79
    initializeApp
    -0.78
    kanak
    -0.77
    quarelle
    -0.76
    jc
    -0.76
    couverte
    -0.75
    ộp
    -0.74
    tiglie
    -0.73
    getClass
    -0.73
    POSITIVE LOGITS
     support
    1.98
    SUPPORT
    1.63
     supporting
    1.61
     saling
    1.59
     help
    1.54
     supports
    1.51
     SUPPORT
    1.51
    互相
    1.50
     complement
    1.48
    support
    1.45
    Activations Density 0.026%

    No Known Activations