© 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. 71459
    Prev
    Next
    INDEX
    Explanations

    different expressions

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

    The neuron fires on numerical tokens and numeric expressions (e.g. standalone numbers or measurements).

    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
     if
    -1.38
     Wirken
    -1.27
    heds
    -1.24
     illetve
    -1.20
     it
    -1.20
    continue
    -1.20
    ventajas
    -1.20
     processes
    -1.17
     circumstances
    -1.13
     bardzo
    -1.13
    POSITIVE LOGITS
     сахара
    1.35
    ׇ
    1.34
     молока
    1.16
     τὴν
    1.16
     RISERV
    1.16
     τῆς
    1.15
    ⇡
    1.13
     administração
    1.13
     aquesta
    1.12
     разом
    1.11
    Activations Density 0.014%

    No Known Activations