© 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. 130789
    Prev
    Next
    INDEX
    Explanations

    website links and code snippets

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

    The neuron strongly activates on tokens that are part of document or section titles/headlines.

    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
    »،
    -1.74
     various
    -1.59
    ność
    -1.59
    re
    -1.57
     некоторые
    -1.56
    ut
    -1.55
     lze
    -1.53
    
    -1.53
    τες
    -1.51
     which
    -1.49
    POSITIVE LOGITS
    0
    2.05
    6
    2.02
    5
    2.00
    8
    1.89
     БО
    1.81
    7
    1.81
    versace
    1.80
     or
    1.77
     ideen
    1.75
    valentino
    1.74
    Activations Density 0.531%

    No Known Activations