© 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. 113558
    Prev
    Next
    INDEX
    Explanations

    door related words

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

    The neuron consistently lights up on the second half of hyphenated compounds (e.g. “open-door,” “closed-door,” “G-went,” “Ashton-Gate”).

    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
    }
    -3.06
    к
    -2.47
    s
    -2.27
    ি
    -2.23
     尔
    -2.22
    お店
    -2.13
    ～～～
    -2.11
    та
    -2.11
    頂き
    -2.11
    多的
    -2.09
    POSITIVE LOGITS
    趼
    2.45
    鈊
    2.27
    
    2.25
    翆
    2.23
    葎
    2.20
    凩
    2.17
    乄
    2.14
     scow
    2.13
    鈇
    2.08
    🛇
    2.06
    Activations Density 0.001%

    No Known Activations