© 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. 34-GEMMASCOPE-RES-131K
    7. 55799
    Prev
    Next
    INDEX
    Explanations

    always followed by verb

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

    The neuron activates on occurrences of the word “always.”

    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
     reconoce
    -0.76
     recognizable
    -0.74
    doesn
    -0.74
    cterms
    -0.73
     available
    -0.73
     a
    -0.73
     TERMS
    -0.72
     folhe
    -0.72
     doesn
    -0.71
     нельзя
    -0.71
    POSITIVE LOGITS
     liked
    2.16
     loved
    2.05
    Loved
    1.72
     hated
    1.53
     Loved
    1.52
     thought
    1.48
     wanted
    1.28
    liked
    1.27
    loved
    1.27
     wondered
    1.25
    Activations Density 0.018%

    No Known Activations