© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15476
    Prev
    Next
    INDEX
    Explanations

    working together

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

    The neuron fires on words and phrases that signal collective action or togetherness—i.e. collaboration, group unity, and team effort.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ાર્થી
    1.03
    ,_-
    1.02
     fiance
    0.89
    дила
    0.88
     말미암
    0.82
    dioxide
    0.82
     overboard
    0.81
     Eritrea
    0.81
     erwäh
    0.80
    /-}$
    0.80
    POSITIVE LOGITS
    ل
    1.33
    ة
    1.23
    a
    1.16
     मिलकर
    1.14
     Together
    1.13
    द
    1.13
     collectively
    1.09
    ing
    1.09
    l
    1.08
    n
    1.07
    Activations Density 0.367%

    No Known Activations