© 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. 58822
    Prev
    Next
    INDEX
    Explanations

    retreat

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

    The neuron responds primarily to numeric tokens (numbers or digit sequences) in the text.

    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
    excitation
    -0.78
     tonight
    -0.77
     dziś
    -0.75
    清洗
    -0.74
     child
    -0.74
     voordelen
    -0.74
     today
    -0.73
    freq
    -0.72
     traffic
    -0.71
     çocuk
    -0.71
    POSITIVE LOGITS
     retreat
    3.58
     retreats
    3.20
     Retreat
    2.81
     retreated
    2.09
     retreating
    2.08
     retraite
    1.75
    Ret
    1.69
     retiro
    1.67
     getaway
    1.58
    ret
    1.54
    Activations Density 0.033%

    No Known Activations