© 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. 73643
    Prev
    Next
    INDEX
    Explanations

    journal citations and DOIs

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

    The neuron activates on double‐hyphen sequences (“--”), i.e. the dash‐style separators used in page or number ranges.

    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
     who
    -1.05
     since
    -0.99
     TextEditing
    -0.98
     havaianas
    -0.96
     espres
    -0.96
    ntgen
    -0.96
     達
    -0.96
    是怎么回事
    -0.94
     selaku
    -0.94
     devine
    -0.93
    POSITIVE LOGITS
    hinh
    1.09
     krwi
    1.03
    ąpi
    1.01
    gegevens
    1.00
     cometido
    0.99
     homens
    0.98
    spania
    0.98
    出色
    0.98
    spod
    0.97
     namelijk
    0.96
    Activations Density 0.006%

    No Known Activations