© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71646
    Prev
    Next
    INDEX
    Explanations

    sequences ending in eutectic, luteal, elute

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

    The neuron activates for the word "ute" and its variations like "elute," "pollute," "eutectic," "executeScript," and "Lutetian," particularly when they appear in technical or scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    I
    -3.08
    翃
    -2.81
    "
    -2.66
    the
    -2.22
     наша
    -2.16
     propel
    -2.14
     hoher
    -2.11
     succumb
    -2.11
    曾在
    -2.11
    知道
    -2.03
    POSITIVE LOGITS
     anún
    2.73
    ";
    2.70
     It
    2.58
    ちゃんは
    2.55
    锒
    2.50
    ute
    2.47
    洳
    2.47
    屣
    2.42
     palio
    2.42
    Ꮬ
    2.39
    Activations Density 0.013%

    No Known Activations