© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13213
    Prev
    Next
    INDEX
    Explanations

    politicians

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

    The neuron strongly activates on occurrences of the word “politicians.”

    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
    或者
    -2.63
    蒾
    -2.41
    или
    -2.39
     *
    -2.28
    )
    -2.25
     selben
    -2.23
    ）：
    -2.20
    ⟝
    -2.16
     asses
    -2.16
    .”
    -2.16
    POSITIVE LOGITS
    .
    4.00
    {
    2.98
    鸸
    2.63
    酲
    2.52
    隂
    2.38
    </h1>
    2.36
    狆
    2.31
    2.30
     أيام
    2.25
     矢量
    2.22
    Activations Density 0.005%

    No Known Activations