© 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. 47913
    Prev
    Next
    INDEX
    Explanations

    Does questions

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

    The neuron detects occurrences of the question word “Does,” especially at the start of queries.

    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
     biele
    -2.36
    ]
    -2.31
     Hinblick
    -2.22
    }
    -2.20
    lloworld
    -2.20
     августа
    -2.19
     帅气
    -2.19
    viembre
    -2.19
     implementar
    -2.16
    釓
    -2.13
    POSITIVE LOGITS
    It
    2.56
    2
    2.41
    useNewUrlParser
    2.38
    {
    2.38
    that
    2.38
    Doesn
    2.31
    ‘
    2.30
    9
    2.30
    ︓
    2.17
    ются
    2.08
    Activations Density 0.018%

    No Known Activations