© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27058
    Prev
    Next
    INDEX
    Explanations

    version numbers and release candidates

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

    The neuron strongly activates on numeric tokens—especially multi‐part digit sequences and decimals—i.e. software version numbers.

    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
     الحكومة
    -1.22
    如果
    -1.20
    INFINITY
    -1.10
    ampiyon
    -1.10
    national
    -1.06
    疫
    -1.05
    “
    -1.05
    涉及
    -1.05
    政治
    -1.05
    重生
    -1.05
    POSITIVE LOGITS
     yesterday
    1.37
     latest
    1.29
     today
    1.16
     recently
    1.14
     ontem
    1.05
    набор
    1.04
    ♲
    1.03
     کرد
    1.02
    最新的
    1.02
     escritorio
    1.01
    Activations Density 0.073%

    No Known Activations