© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64596
    Prev
    Next
    INDEX
    Explanations

    following specific designations

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

    The neuron is detecting high‐frequency English function words (common stop words such as “the,” “a,” “by,” “which,” “are,” etc.).

    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
     объяви
    -1.06
     undersigned
    -1.06
     artikelen
    -1.05
    -1.04
     različ
    -1.03
     nélk
    -1.02
    ρούν
    -1.02
    方の
    -1.02
    recently
    -1.02
     wzglę
    -1.00
    POSITIVE LOGITS
     use
    1.20
     adding
    1.19
     changes
    1.16
     repeated
    1.13
     results
    1.13
     slight
    1.13
     increase
    1.10
     result
    1.07
     is
    1.07
     reduction
    1.06
    Activations Density 0.524%

    No Known Activations