© 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. 19335
    Prev
    Next
    INDEX
    Explanations

    dates and creation metadata

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

    This neuron never activates on any token.

    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
     for
    -1.57
     gainera
    -1.54
    六年
    -1.51
    礪
    -1.45
    träglich
    -1.43
    After
    -1.41
     if
    -1.39
    春天
    -1.38
     близь
    -1.37
     traseiro
    -1.36
    POSITIVE LOGITS
    ates
    1.47
    ཥ
    1.45
    "}}
    1.36
     culturales
    1.35
     contando
    1.29
     Β
    1.28
    useNewUrlParser
    1.28
     Cultural
    1.27
     "";
    1.27
    THAT
    1.26
    Activations Density 0.028%

    No Known Activations