© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15590
    Prev
    Next
    INDEX
    Explanations

    closing punctuation followed by definition

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

    The neuron fires on words that occur as section or document titles/headings.

    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
    g
    -1.20
    ed
    -1.20
    note
    -1.17
    w
    -1.16
    list
    -1.13
    e
    -1.12
    time
    -1.10
    ≲
    -1.10
    ；
    -1.10
    ni
    -1.09
    POSITIVE LOGITS
     its
    1.33
     bekämp
    1.32
     obuv
    1.21
     músculo
    1.10
     keker
    1.09
     químico
    1.08
    Földrajz
    1.08
    』(
    1.07
     ofici
    1.05
     distribuidor
    1.05
    Activations Density 0.003%

    No Known Activations