© 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. 34-GEMMASCOPE-RES-131K
    4. 23892
    Prev
    Next
    INDEX
    Explanations

    actually

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

    This neuron fires on the very first few tokens of a new text segment, marking the opening words of each document or post.

    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
    eseorang
    -1.13
     塗装
    -0.99
     inoltre
    -0.98
     (!$
    -0.86
    걷
    -0.85
     nữa
    -0.84
    ,}
    -0.83
    tipo
    -0.82
     sehr
    -0.80
    Ƙ
    -0.77
    POSITIVE LOGITS
     actually
    9.25
    actually
    7.47
    Actually
    7.34
     Actually
    6.78
     actual
    5.66
     ACTUALLY
    5.25
    其實
    4.94
    actual
    4.75
    其实
    4.72
     aslında
    4.72
    Activations Density 0.436%

    No Known Activations