© 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. 110895
    Prev
    Next
    INDEX
    Explanations

    questions starting with is this

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

    The neuron detects the auxiliary “Is” at the start of yes/no questions.

    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
    9
    -2.59
    3
    -2.25
     and
    -2.11
    2
    -2.03
    7
    -2.02
    6
    -2.00
    1
    -1.98
    ].
    -1.96
    8
    -1.95
    4
    -1.95
    POSITIVE LOGITS
     a
    4.19
     an
    2.19
    ᡴ
    1.98
     denoted
    1.95
     regarded
    1.92
     another
    1.91
    磲
    1.87
     going
    1.87
     “
    1.82
     also
    1.80
    Activations Density 0.012%

    No Known Activations