© 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. 65068
    Prev
    Next
    INDEX
    Explanations

    conjunctions and clauses

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

    This neuron fires on tokens that occur in explanatory or advisory statements—i.e. sentences giving practical instructions or guidance.

    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
     également
    -0.99
    ))=\
    -0.96
     során
    -0.94
    etna
    -0.94
     alimentación
    -0.86
     fuit
    -0.86
    Ethylbenzene
    -0.85
     burch
    -0.85
     ſur
    -0.84
     steg
    -0.84
    POSITIVE LOGITS
     having
    7.50
    Having
    5.66
     Having
    5.66
    having
    5.28
     HAVING
    4.03
     ayant
    3.63
     иметь
    3.52
     داشتن
    3.42
     tener
    3.27
     avere
    3.13
    Activations Density 0.147%

    No Known Activations