© 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. 22-GEMMASCOPE-RES-131K
    7. 92949
    Prev
    Next
    INDEX
    Explanations

    css class names and values

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

    This neuron activates on numeric tokens (e.g. sizes or counts like “100”, “200”, “33.33” etc.), effectively spotting numeric literals in code or style declarations.

    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
     that
    -1.27
     možno
    -1.14
     vienas
    -1.09
     osserva
    -1.05
     to
    -1.05
    positor
    -1.02
     because
    -1.01
    ➹
    -1.01
     pomocou
    -1.01
    〜〜
    -1.00
    POSITIVE LOGITS
    !
    1.07
    itele
    0.96
     shady
    0.93
    螨
    0.91
    兑换
    0.91
     já
    0.90
     berätt
    0.90
    össä
    0.88
    ⇀
    0.87
     fanns
    0.87
    Activations Density 0.003%

    No Known Activations