© 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. 105047
    Prev
    Next
    INDEX
    Explanations

    hats and context

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

    The neuron activates on mentions of hats or headwear.

    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
     ”
    -2.17
    </td>
    -2.17
     zullen
    -2.16
    ”.
    -2.11
    而在
    -2.09
    1
    -2.09
    ↵
    -2.09
    ⤞
    -2.05
     –
    -2.03
    就此
    -1.98
    POSITIVE LOGITS
    ꜆
    2.73
     hats
    2.53
     manoeuvre
    2.22
    enablog
    2.20
     fue
    2.16
    횃
    2.16
    Z
    2.16
    ጺ
    2.16
     ayakkab
    2.14
    L
    2.14
    Activations Density 0.002%

    No Known Activations