© 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. 10-GEMMASCOPE-RES-131K
    4. 127477
    Prev
    Next
    INDEX
    Explanations

    phrases ending in punctuation

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

    The neuron is keyed to document structure markers—titles, headings, and section‐introducing phrases (e.g. “Also,” “Said:”, questions “Q:”, “Get ready to…”) rather than ordinary running text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -2.05
    其他的
    -1.55
     чтобы
    -1.53
     palk
    -1.45
    已经
    -1.38
     osal
    -1.38
     already
    -1.37
    AN
    -1.35
    他の
    -1.32
    ÚS
    -1.32
    POSITIVE LOGITS
     about
    2.28
    𝐫
    1.51
     広場
    1.38
    riezmann
    1.35
    himself
    1.35
    𝐺
    1.34
     sqlSession
    1.34
    grew
    1.34
    èdent
    1.33
    oved
    1.31
    Activations Density 0.192%

    No Known Activations