© 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. 10-GEMMASCOPE-RES-131K
    7. 47614
    Prev
    Next
    INDEX
    Explanations

    alongside

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

    The neuron fires on occurrences of the token “alongside” (and its subword fragments), marking contexts where one entity is working or appearing together with another.

    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
     to
    -1.86
     their
    -1.72
    ījum
    -1.69
    нодоро
    -1.63
    なのですが
    -1.60
     Após
    -1.58
    ïlande
    -1.57
    푣
    -1.55
    钜
    -1.54
    ⇰
    -1.52
    POSITIVE LOGITS
    5
    2.23
    7
    2.06
    0
    1.88
    4
    1.84
    '
    1.78
    9
    1.78
    6
    1.77
    ⑊
    1.67
    8
    1.66
    2
    1.60
    Activations Density 0.028%

    No Known Activations