© 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. 72125
    Prev
    Next
    INDEX
    Explanations

    verb followed by preposition

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

    This neuron identifies words that begin list items or bullet-style entries, such as the first token immediately following a hyphen or other list marker.

    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
     desplaz
    -1.24
     tomber
    -1.16
    蹓
    -1.13
     délicieux
    -1.12
    皝
    -1.10
    极其
    -1.09
    exactly
    -1.09
    んですよね
    -1.08
     tē
    -1.06
    geführten
    -1.05
    POSITIVE LOGITS
    これも
    1.16
    こちらも
    1.14
    l
    1.13
    el
    1.13
     again
    1.12
     includes
    1.12
     is
    1.11
     may
    1.09
    。
    1.07
    in
    1.06
    Activations Density 0.051%

    No Known Activations