© 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. 60691
    Prev
    Next
    INDEX
    Explanations

    controller

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

    The neuron activates on occurrences of the word “controller.”

    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
    s
    -2.88
    e
    -2.81
    2
    -2.42
    )
    -2.34
    或是
    -2.31
    ндарт
    -2.20
     yako
    -2.19
     Your
    -2.08
    蹋
    -2.06
    Akhir
    -2.05
    POSITIVE LOGITS
    ”;
    3.39
    !”
    2.95
    ”)
    2.91
    ჻
    2.91
    
    2.83
                                
    2.69
        
    2.67
    );
    2.66
    ”:
    2.66
    为你
    2.59
    Activations Density 0.022%

    No Known Activations