© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73203
    Prev
    Next
    INDEX
    Explanations

    swings, beds, gazebos, gondolas

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

    The neuron fires on mentions of furniture‐ or structure‐type words referring to things you sit, lie, swing, or otherwise rest in (e.g. swings, beds, hammocks, seats, gazebos, gondolas).

    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
    艄
    -2.14
    ﮩ
    -1.91
    Ольга
    -1.91
    2
    -1.91
    have
    -1.91
     Betrach
    -1.90
    ρους
    -1.89
    Здра
    -1.89
    噐
    -1.88
    pareja
    -1.87
    POSITIVE LOGITS
    ↵
    2.42
    ↵↵
    2.19
    ]
    2.09
    <i>
    2.00
    ]$
    1.98
    [
    1.77
    内的
    1.77
    t
    1.74
    ).
    1.70
     как
    1.66
    Activations Density 0.004%

    No Known Activations