© 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. 22-GEMMASCOPE-RES-131K
    7. 34872
    Prev
    Next
    INDEX
    Explanations

    specific scientific concepts

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

    The neuron activates on technical descriptions contrasting local versus global levels of detail (e.g., “local‐level detail” versus “global configuration”).

    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
     souver
    -0.85
    netbeans
    -0.85
    喩
    -0.84
     passend
    -0.84
     warped
    -0.84
    ঊ
    -0.83
    姦
    -0.82
    archiviato
    -0.82
     nimmer
    -0.81
    anshi
    -0.81
    POSITIVE LOGITS
     rather
    1.26
    よりも
    1.07
     דו
    1.00
     plutôt
    0.99
     aspects
    0.96
     יותר
    0.94
     gegenüber
    0.94
     than
    0.88
     niż
    0.88
    पाद
    0.87
    Activations Density 0.091%

    No Known Activations