© 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. 10266
    Prev
    Next
    INDEX
    Explanations

    prefix "Hil"

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

    The neuron responds to any occurrence of the letter sequence “hil” (in any context or casing) within a word.

    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
    戩
    -3.13
    Ꮟ
    -3.06
    ญี่ป
    -2.97
    ↑↑↑</
    -2.81
    Donativos
    -2.80
    灕
    -2.78
    灩
    -2.70
    
    -2.70
     divertidas
    -2.69
    焄
    -2.58
    POSITIVE LOGITS
    .
    4.41
    埽
    3.50
    </strong>
    3.23
    1
    3.05
    We
    3.00
    }$
    2.75
    一旁
    2.66
    齮
    2.61
    </h3>
    2.59
    何度も
    2.59
    Activations Density 0.003%

    No Known Activations