© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 299
    Prev
    Next
    INDEX
    Explanations

    plasma levels and oxidative stress

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

    forum post quotation patterns, particularly when a user quotes a previous message in a discussion thread.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects quoting markers in online discussions or emails, such as “wrote:” or “Quote:”.

    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
    providedIn
    -1.68
     to
    -1.52
    haviours
    -1.33
    NameExpr
    -1.32
    racy
    -1.27
    StandardCharsets
    -1.23
     in
    -1.22
    bigr
    -1.20
     безопасность
    -1.17
    bottomRight
    -1.17
    POSITIVE LOGITS
    ↵
    1.55
     Funktionalität
    1.41
    不仅仅
    1.41
    取决
    1.38
     gethan
    1.37
    不仅
    1.31
     elevación
    1.28
     stück
    1.20
     disminu
    1.19
    Prova
    1.17
    Activations Density 0.000%

    No Known Activations