© 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. 10-GEMMASCOPE-RES-131K
    7. 1669
    Prev
    Next
    INDEX
    Explanations

    various reasons, conditions, circumstances

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

    The neuron detects the word “reasons” when it appears in phrases like “for various reasons,” “for a variety of reasons,” or “for a number of reasons.”

    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
     any
    -1.45
     time
    -1.35
    ()',
    -1.23
    enfer
    -1.22
    Ohne
    -1.19
     for
    -1.18
    izieren
    -1.18
    Idem
    -1.15
    沺
    -1.14
    Schritt
    -1.13
    POSITIVE LOGITS
     everyone
    1.35
    emptions
    1.23
     everything
    1.23
    っているので
    1.13
    hability
    1.10
    どく
    1.09
    THE
    1.09
     жизнен
    1.06
    ği
    1.05
     всем
    1.05
    Activations Density 0.111%

    No Known Activations