© 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. 25963
    Prev
    Next
    INDEX
    Explanations

    financial assets and balance information

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

    The neuron activates on numeric expressions (especially multi‐digit numbers, monetary amounts, and other quantified values).

    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
     från
    -1.12
     wilden
    -1.11
    บน
    -1.09
    ätigung
    -1.09
     verhind
    -1.07
     anglès
    -1.05
    啊
    -1.05
     heiligen
    -1.05
    egli
    -1.05
     to
    -1.04
    POSITIVE LOGITS
    capace
    1.39
    recent
    1.29
     assets
    1.29
     recently
    1.24
     recent
    1.19
    seamnă
    1.19
    剧照
    1.17
    📻
    1.13
     Gato
    1.13
    Voyage
    1.13
    Activations Density 0.009%

    No Known Activations