© 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. 112874
    Prev
    Next
    INDEX
    Explanations

    following 'a' or 'an'

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

    The neuron consistently fires on the single-token “a.”

    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
    ’
    -1.52
     With
    -1.41
     surprisingly
    -1.21
     Surprisingly
    -1.19
     erzählen
    -1.19
     interestingly
    -1.17
     Without
    -1.16
     bemerkt
    -1.15
     kullanılır
    -1.15
     articulate
    -1.14
    POSITIVE LOGITS
    )?;
    1.48
    噲
    1.46
     recommandons
    1.46
    Ꮷ
    1.45
     you
    1.43
    sores
    1.41
     meld
    1.39
     også
    1.35
    iffance
    1.34
    UNITIES
    1.30
    Activations Density 0.124%

    No Known Activations