© 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. 22-GEMMASCOPE-RES-131K
    7. 104347
    Prev
    Next
    INDEX
    Explanations

    elements and states

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

    The neuron activates on specialized technical jargon—especially domain‐specific nouns and quantitative terms—typical of engineering or patent descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    n
    -1.55
    }
    -1.51
     doesn
    -1.48
     isn
    -1.48
     then
    -1.45
     didn
    -1.40
    l
    -1.38
    Un
    -1.31
    N
    -1.30
    d
    -1.30
    POSITIVE LOGITS
     of
    1.97
     БО
    1.74
     that
    1.64
     histó
    1.64
     which
    1.63
     rése
    1.57
     vín
    1.55
     pérd
    1.52
     favoris
    1.52
    aning
    1.51
    Activations Density 0.289%

    No Known Activations