© 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. 10-GEMMASCOPE-RES-131K
    4. 120037
    Prev
    Next
    INDEX
    Explanations

    to

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

    The neuron is keyed to occurrences of movement-to-place constructions—especially the “go to (the) X” pattern.

    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
    which
    -2.41
    3
    -2.31
     ingenting
    -2.05
     groote
    -2.03
    selbe
    -2.03
     ceket
    -2.02
    not
    -1.99
    ti
    -1.98
    on
    -1.98
    were
    -1.98
    POSITIVE LOGITS
     to
    3.02
     and
    2.53
     fashioned
    2.27
    凊
    1.98
     くれ
    1.91
    
    1.91
    नलोड
    1.84
    元的
    1.84
     maior
    1.79
    俭
    1.79
    Activations Density 0.013%

    No Known Activations