© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55604
    Prev
    Next
    INDEX
    Explanations

    liquid followed by specific nouns

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

    The neuron predominantly activates on the token “Liquid,” i.e. it detects occurrences of that word.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     alguns
    -0.90
     Biggest
    -0.90
    的事情
    -0.89
     grumpy
    -0.89
     envejec
    -0.88
     Exquisite
    -0.88
     Dirty
    -0.87
     startling
    -0.87
     Brings
    -0.86
    REDU
    -0.85
    POSITIVE LOGITS
    liquid
    2.06
    ambar
    1.55
     Liquid
    1.52
     liquid
    1.36
    Liquid
    1.32
    ators
    1.16
     LIQUID
    1.13
     assets
    1.09
     vaisselle
    1.08
    ator
    1.04
    Activations Density 0.022%

    No Known Activations