© 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. 67149
    Prev
    Next
    INDEX
    Explanations

    specific parts or elements

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

    The neuron fires on relatively uncommon, content-bearing words (especially technical or domain-specific terms) rather than on common function words.

    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
    pozycji
    -0.96
    糰
    -0.92
     cuál
    -0.90
    妧
    -0.89
    jeremy
    -0.88
     dosta
    -0.86
     miesto
    -0.85
    Só
    -0.85
     Misalnya
    -0.85
     například
    -0.84
    POSITIVE LOGITS
     aspect
    1.84
     aspects
    1.80
    部分
    1.50
     part
    1.41
     elements
    1.40
     portion
    1.36
     functionality
    1.29
     части
    1.23
     portions
    1.22
     status
    1.17
    Activations Density 0.233%

    No Known Activations