© 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. 102809
    Prev
    Next
    INDEX
    Explanations

    customize my, your, it

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

    The neuron fires strongly on the morpheme “custom” and its inflected forms (e.g. custom, customize, customizer), i.e. tokens related to customization.

    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
     You
    -3.00
    2
    -2.95
     Of
    -2.75
     This
    -2.73
     blaue
    -2.66
     Then
    -2.64
    }
    -2.64
    mathrm
    -2.56
    大概
    -2.56
     Would
    -2.55
    POSITIVE LOGITS
    芣
    3.22
    以上です
    3.05
    ⚣
    2.97
    结语
    2.97
    酹
    2.94
    媜
    2.86
    ᠂
    2.84
     แดง
    2.80
     твои
    2.75
    鱨
    2.75
    Activations Density 0.007%

    No Known Activations