© 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. 34-GEMMASCOPE-RES-131K
    7. 103440
    Prev
    Next
    INDEX
    Explanations

    IEDM Proc. and cdk

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

    The neuron activates on numeric tokens (e.g. section numbers, year citations, page numbers)—i.e. it detects standalone 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_34/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
    ⠃
    -0.96
    が違う
    -0.91
    ͊
    -0.88
    irtschaft
    -0.86
     involvement
    -0.85
    urlopen
    -0.85
     gäng
    -0.82
    って何
    -0.82
     ثق
    -0.81
    ᴰ
    -0.79
    POSITIVE LOGITS
     graphique
    0.96
     workshop
    0.92
     Workshops
    0.91
    かで
    0.89
    IRECT
    0.88
     workshops
    0.82
     anglais
    0.81
    が含ま
    0.81
     nesten
    0.80
     Workshop
    0.79
    Activations Density 0.041%

    No Known Activations