© 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. 61025
    Prev
    Next
    INDEX
    Explanations

    Questions and introductions

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

    The neuron responds to in‐text citation markers (e.g., “[ @… ]”).

    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
     in
    -2.53
     from
    -2.08
     while
    -1.93
     when
    -1.91
     before
    -1.88
     by
    -1.83
     during
    -1.80
     provides
    -1.77
     after
    -1.77
     facilitates
    -1.77
    POSITIVE LOGITS
     jednej
    1.94
     tà
    1.88
    謦
    1.87
     anderen
    1.76
     纹身
    1.75
    艄
    1.75
    zzlement
    1.74
     stadion
    1.71
    鹟
    1.70
     klimat
    1.66
    Activations Density 0.000%

    No Known Activations