© 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. 20407
    Prev
    Next
    INDEX
    Explanations

    quite a bit

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

    The neuron strongly activates on the small filler word “bit.”

    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
     motocicletas
    -2.11
    ⽥
    -1.91
    értelmű
    -1.81
    Однако
    -1.74
    {{-
    -1.64
    𓆏
    -1.62
     deceptive
    -1.62
    setzt
    -1.61
    ↵
    -1.61
    colgante
    -1.59
    POSITIVE LOGITS
    l
    2.14
    </strong>
    2.13
     was
    2.03
    ?"
    2.03
    .,
    1.89
    this
    1.77
    <bos>
    1.77
    ,"
    1.75
    )
    1.74
    p
    1.73
    Activations Density 0.001%

    No Known Activations