© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75032
    Prev
    Next
    INDEX
    Explanations

    after a quote

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

    The neuron flags the markers and tokens that introduce quoted or highlighted blocks—e.g. opening quotation marks, the “Q:” and title‐style words—i.e. it detects the start of a blockquote or question heading.

    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
     ganske
    -1.17
     allerede
    -1.05
     within
    -1.04
     sehr
    -1.00
    Going
    -0.99
     которы
    -0.98
    Hvordan
    -0.98
     with
    -0.95
     difund
    -0.95
     containing
    -0.94
    POSITIVE LOGITS
     …
    1.21
     then
    1.12
     also
    1.09
     ...
    1.09
    ]
    1.05
    わせる
    1.03
     uniformed
    1.03
    ≈
    1.03
    ┇
    1.00
     Prozent
    0.99
    Activations Density 0.029%

    No Known Activations