© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130151
    Prev
    Next
    INDEX
    Explanations

    information from sources

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

    The neuron detects occurrences of “hear from” (or “heard from”) phrases indicating that someone is reporting or receiving information from a source.

    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
    ↵
    -1.95
    鈊
    -1.93
     если
    -1.85
     temos
    -1.59
     wichtigste
    -1.55
     nếu
    -1.54
    zsef
    -1.52
    钜
    -1.51
    zwald
    -1.50
    着她
    -1.48
    POSITIVE LOGITS
     about
    1.96
    ha
    1.73
     perfet
    1.59
     concernés
    1.59
    ter
    1.55
    s
    1.52
    on
    1.52
    .」
    1.50
    er
    1.49
    ()).
    1.48
    Activations Density 0.007%

    No Known Activations