© 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. 90006
    Prev
    Next
    INDEX
    Explanations

    abstract noun following "the"

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

    This neuron strongly activates on four-digit numeric tokens (e.g. years or similar 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
     dezelfde
    -1.30
     tantangan
    -1.29
    yya
    -1.19
    givers
    -1.18
     pengobatan
    -1.16
     بهترین
    -1.15
     pikiran
    -1.15
    ZIONI
    -1.14
     during
    -1.12
    íteni
    -1.12
    POSITIVE LOGITS
     fact
    2.73
     amount
    2.36
     lack
    2.31
     ability
    2.31
     inability
    2.27
     absence
    2.23
     possibility
    2.13
     presence
    2.08
     way
    2.02
     constant
    1.96
    Activations Density 0.082%

    No Known Activations