© 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. 34-GEMMASCOPE-RES-131K
    7. 47577
    Prev
    Next
    INDEX
    Explanations

    words starting with equi

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

    The neuron fires on tokens beginning with the letter sequence “equ” (e.g. equi-, equ-, EQU-).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     uncommon
    -0.91
     highest
    -0.81
    訟
    -0.81
    許
    -0.74
     höchsten
    -0.74
    Importing
    -0.73
     quedará
    -0.73
     höchste
    -0.72
    tistas
    -0.71
    ุ่ง
    -0.70
    POSITIVE LOGITS
     Equ
    1.37
     EQ
    1.09
    Equ
    1.06
     Equilibrium
    1.03
     EQU
    1.01
     eq
    1.00
     equ
    0.99
     Equest
    0.97
     equili
    0.93
     Eq
    0.89
    Activations Density 0.024%

    No Known Activations