© 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. 22-GEMMASCOPE-RES-131K
    7. 67003
    Prev
    Next
    INDEX
    Explanations

    also, and, or, to

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

    This neuron detects high-frequency connecting words (common conjunctions and discourse markers) such as “but,” “also,” “and,” “to,” and “then.”

    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
     grasas
    -1.21
     mỗi
    -1.17
     каждой
    -1.16
     этой
    -1.11
     sorpresas
    -1.09
     بنابراین
    -1.08
     guerras
    -1.07
     algodón
    -1.05
     repuesto
    -1.05
     этого
    -1.03
    POSITIVE LOGITS
     to
    1.43
     ideen
    1.21
     simpel
    1.11
    having
    1.09
     also
    1.05
     additionally
    1.04
    агностика
    1.04
     being
    1.04
    kende
    1.02
    でもあります
    1.02
    Activations Density 0.085%

    No Known Activations