© 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. 10963
    Prev
    Next
    INDEX
    Explanations

    wrote

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

    This neuron detects the verb “wrote” used to attribute or report authorship.

    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
    ities
    -2.41
    𐬹
    -2.38
    {
    -2.36
    PasswordEncoder
    -2.33
     abandon
    -2.22
    }
    -2.16
    ',
    -2.16
     wzglę
    -2.11
    BeNil
    -2.11
    笄
    -2.05
    POSITIVE LOGITS
     wrote
    2.55
    猡
    2.48
     inverno
    2.38
     tetapi
    2.34
    -
    2.30
     recentemente
    2.28
    蜴
    2.22
     recently
    2.19
    adds
    2.14
    臈
    2.13
    Activations Density 0.006%

    No Known Activations