© 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. 105087
    Prev
    Next
    INDEX
    Explanations

    as ... it

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

    The neuron fires on words and short phrases that express approximation or comparison (e.g. “about,” “same,” “as … as,” “on par with”).

    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
    `,
    -2.13
    ),
    -1.84
    ván
    -1.75
    )]
    -1.66
     $]$
    -1.65
     帅气
    -1.65
    нью
    -1.61
    ﴾
    -1.61
    )]{
    -1.61
    )/
    -1.61
    POSITIVE LOGITS
    '
    2.02
    6
    2.00
    8
    1.80
    ',
    1.75
    3
    1.71
    0
    1.65
    s
    1.65
    9
    1.62
    ot
    1.55
    os
    1.55
    Activations Density 0.013%

    No Known Activations