© 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. 34-GEMMASCOPE-RES-131K
    7. 106996
    Prev
    Next
    INDEX
    Explanations

    and, but, especially

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

    The neuron fires on numeric tokens, i.e. any standalone 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_34/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
     diego
    -1.25
     gosto
    -1.18
    americanas
    -1.16
    łym
    -1.14
    ：“……”
    -1.12
    าก็
    -1.12
     aspectos
    -1.08
     används
    -1.07
    łego
    -1.06
     climático
    -1.05
    POSITIVE LOGITS
     and
    3.19
     but
    1.95
     both
    1.89
     especially
    1.88
     including
    1.62
    ทั้ง
    1.55
     particularly
    1.46
     zarówno
    1.45
     along
    1.29
     especialmente
    1.27
    Activations Density 0.084%

    No Known Activations