© 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. 92890
    Prev
    Next
    INDEX
    Explanations

    publication details and references

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

    The neuron selectively activates on multi-digit numbers appearing in reference citations (e.g., volume, issue, page, or year numbers).

    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
     a
    -1.41
    際に
    -1.27
     هار
    -1.13
     actief
    -1.12
     genauso
    -1.10
    벳
    -1.07
     acabamento
    -1.07
     belangrijk
    -1.06
     lixo
    -1.06
     banheiro
    -1.05
    POSITIVE LOGITS
    颐
    1.10
    それに
    1.06
    つまり
    1.03
    Suara
    1.02
    それも
    1.00
    jú
    1.00
    特に
    0.98
    もあります
    0.97
    歯科
    0.96
    ntä
    0.96
    Activations Density 0.045%

    No Known Activations