© 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. 71741
    Prev
    Next
    INDEX
    Explanations

    code objects and operations

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

    The neuron fires on numeric tokens (i.e. digit sequences or numeric literals).

    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
     kolik
    -1.17
     which
    -1.12
     that
    -1.10
    迥
    -1.09
     druga
    -1.09
     TÉCN
    -1.05
     ktore
    -1.03
     SOBRE
    -1.02
     MEJOR
    -1.02
     kommit
    -1.00
    POSITIVE LOGITS
    などを
    1.02
     üblichen
    1.01
    を
    1.00
    れています
    0.98
    elf
    0.96
     يج
    0.94
    níku
    0.91
     geleg
    0.90
    ストラリア
    0.89
     россий
    0.89
    Activations Density 0.005%

    No Known Activations