© 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. 22-GEMMASCOPE-RES-131K
    7. 128583
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on occurrences of the preposition “of.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Q: answers and code fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ätie
    -0.89
    their
    -0.86
     YOUTUBE
    -0.83
    𝐻
    -0.82
     michael
    -0.82
     correspondance
    -0.81
     pengantin
    -0.81
    
    -0.81
    EventArgs
    -0.81
    worfen
    -0.79
    POSITIVE LOGITS
     alkyl
    0.87
     Gerais
    0.85
     parseInt
    0.85
     why
    0.84
    Greetings
    0.81
     índ
    0.80
     removeFrom
    0.80
     proof
    0.80
     getLast
    0.79
    んだけど
    0.79
    Activations Density 0.000%

    No Known Activations