© 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. 72688
    Prev
    Next
    INDEX
    Explanations

    held an, captures, allows users, continues as, is a

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

    The neuron strongly activates on the main clause’s primary verb (the sentence’s head verb).

    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
     preva
    -1.20
     escote
    -1.17
     наши
    -1.09
    ímos
    -1.09
    moine
    -1.09
     = 
    -1.08
    Présentation
    -1.08
     vieta
    -1.06
     yağı
    -1.05
    égories
    -1.05
    POSITIVE LOGITS
     you
    1.26
     they
    1.16
     njia
    1.13
    НИЙ
    1.10
     kosten
    1.09
     blessure
    1.06
     mediante
    1.04
     kopen
    1.03
     douane
    1.01
     at
    1.00
    Activations Density 0.337%

    No Known Activations