© 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. 25656
    Prev
    Next
    INDEX
    Explanations

    ways of working and where

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

    The neuron fires on mentions of structured programs, systems, or procedural mechanisms.

    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
     and
    -1.41
    そして
    -1.13
     أيض
    -1.12
     zawiera
    -1.09
     then
    -1.08
     posiada
    -1.02
     그리고
    -1.00
     milyen
    -0.98
     all
    -0.97
     terwijl
    -0.97
    POSITIVE LOGITS
     whereby
    4.50
     wherein
    3.80
     where
    3.20
    wherein
    3.09
     waarbij
    2.63
     dimana
    2.27
    where
    2.25
     polega
    2.20
     حيث
    2.13
     donde
    2.00
    Activations Density 0.241%

    No Known Activations