© 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. 22-GEMMASCOPE-RES-131K
    7. 64685
    Prev
    Next
    INDEX
    Explanations

    non-english characters and code

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

    The neuron specifically flags occurrences of the standalone numeric literal “0.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     know
    -1.42
     that
    -1.26
     knows
    -1.11
     then
    -1.11
     הם
    -1.09
     appear
    -1.08
     laranja
    -1.04
     both
    -1.03
    はこちらから
    -1.00
     including
    -1.00
    POSITIVE LOGITS
    ヽ
    1.02
    蕾
    1.02
     '',
    0.97
    ใหญ
    0.96
     amat
    0.94
    ennessee
    0.94
     chauffe
    0.93
     kura
    0.93
     phot
    0.91
     personel
    0.91
    Activations Density 0.007%

    No Known Activations