© 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. 104718
    Prev
    Next
    INDEX
    Explanations

    we are

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

    The neuron fires on opening quotation marks and the start of quoted speech.

    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
     its
    -1.61
     também
    -1.54
     also
    -1.54
     it
    -1.53
     también
    -1.51
     them
    -1.48
    gehenden
    -1.39
    también
    -1.38
     גם
    -1.38
     онъ
    -1.37
    POSITIVE LOGITS
     we
    1.34
     dataSnapshot
    1.20
    総評
    1.12
     tawny
    1.05
    зви
    1.03
    ホルモン
    1.02
    すぎる
    1.00
     всего
    1.00
    このように
    0.99
    şil
    0.98
    Activations Density 0.018%

    No Known Activations