© 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. 40318
    Prev
    Next
    INDEX
    Explanations

    describing specific entities or histories

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

    The neuron strongly activates on words that are part of titles or headings (e.g. book, film, article, or section names).

    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
     you
    -1.24
     on
    -1.20
     they
    -1.13
     with
    -1.09
     get
    -1.08
     slightly
    -1.04
     staff
    -1.02
     your
    -1.02
     July
    -1.01
     or
    -1.00
    POSITIVE LOGITS
    polite
    1.27
    Questão
    1.19
    lovely
    1.13
    asking
    1.11
    tells
    1.10
    なぜ
    1.10
    vaila
    1.10
    begins
    1.09
    strange
    1.08
    describing
    1.08
    Activations Density 0.064%

    No Known Activations