© 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. 34358
    Prev
    Next
    INDEX
    Explanations

    utility modules

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

    The neuron activates on import/require paths referring to a “utils” module.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    镠
    -3.39
    kemeja
    -3.06
    硖
    -2.97
     prachtige
    -2.77
    赜
    -2.67
    茕
    -2.63
    
    -2.53
    飏
    -2.52
     शुर
    -2.52
    泺
    -2.48
    POSITIVE LOGITS
    The
    3.58
    In
    3.38
    4
    3.30
    7
    3.28
                        
    3.27
            
    3.22
    8
    3.13
    <i>
    2.88
    With
    2.78
    6
    2.78
    Activations Density 0.006%

    No Known Activations