© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82770
    Prev
    Next
    INDEX
    Explanations

    together with

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

    The neuron activates on the token “together,” effectively detecting occurrences of the word “together” in the text.

    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
     together
    -2.61
    together
    -1.93
     juntos
    -1.64
    Together
    -1.57
     вместе
    -1.37
     insieme
    -1.28
     bersama
    -1.20
     juntas
    -1.20
     Together
    -1.18
     zusammen
    -1.16
    POSITIVE LOGITS
     with
    1.48
     Along
    1.14
     ließen
    1.05
     Again
    1.02
     they
    0.98
     or
    0.97
     constitute
    0.96
     anunciou
    0.94
     Затем
    0.94
     machten
    0.93
    Activations Density 0.011%

    No Known Activations