© 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. 39371
    Prev
    Next
    INDEX
    Explanations

    trash and related concepts

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

    This neuron activates on any token containing the substring “trash” (e.g., trash, trashy, trashing).

    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
    
    -3.59
    焄
    -3.53
    摃
    -3.42
    嫆
    -2.95
    鹋
    -2.94
    趵
    -2.92
    鈊
    -2.92
    喈
    -2.84
    鲧
    -2.83
    』、
    -2.81
    POSITIVE LOGITS
    鬭
    2.48
    ೣ
    2.47
     translateY
    2.34
    ",
    2.31
    {
    2.27
     weitgehend
    2.08
    }
    2.05
    点头
    2.03
    ޚ
    2.03
    ],
    2.02
    Activations Density 0.005%

    No Known Activations