© 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. 39952
    Prev
    Next
    INDEX
    Explanations

    quantifiers including numbers

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

    The neuron is essentially inactive—it never reliably activates on any token.

    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
     several
    -1.26
     Eigentü
    -1.11
    Čo
    -1.09
     it
    -1.05
    ystis
    -1.04
    доль
    -1.00
     zanahoria
    -0.99
     Wohnen
    -0.98
    มัน
    -0.96
    Several
    -0.94
    POSITIVE LOGITS
    それぞれの
    1.09
     jeweils
    0.98
     wobei
    0.98
    wrights
    0.93
    preneurs
    0.91
     Typen
    0.91
    ).—
    0.90
     Beide
    0.90
    wał
    0.87
     syk
    0.85
    Activations Density 0.079%

    No Known Activations