© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67760
    Prev
    Next
    INDEX
    Explanations

    catalog number, CD, 7-inch

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

    The neuron strongly activates on multi‐digit numeric identifiers (e.g. catalog numbers, codes, UPCs).

    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
     consulté
    -1.05
     августа
    -1.04
     who
    -1.02
     мебель
    -1.02
     RSSSF
    -1.00
     commonly
    -0.98
     \&
    -0.98
    אם
    -0.97
     Educação
    -0.96
     nisso
    -0.96
    POSITIVE LOGITS
    Recept
    1.21
    Reak
    1.16
    Absol
    1.13
    等級
    1.10
    Investi
    1.02
    Kval
    1.02
    Gruppen
    1.02
    Responsable
    1.01
    Procedimento
    1.01
    Kommentar
    1.01
    Activations Density 0.002%

    No Known Activations