© 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. 118264
    Prev
    Next
    INDEX
    Explanations

    the followed by section references

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

    The neuron flags multi-digit numerical tokens (especially three- or four-digit 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
    atical
    -1.13
     aço
    -1.08
     både
    -1.07
    atized
    -1.05
    lize
    -1.02
     важ
    -1.00
    ofing
    -1.00
    lessness
    -0.99
     gede
    -0.98
    Sedangkan
    -0.96
    POSITIVE LOGITS
     last
    2.50
     second
    2.19
     third
    2.14
     previous
    2.09
     earlier
    2.08
     fourth
    2.06
     fifth
    1.97
     preceding
    1.91
     next
    1.77
     first
    1.73
    Activations Density 0.073%

    No Known Activations