© 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. 13293
    Prev
    Next
    INDEX
    Explanations

    decrease in quantity

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

    The neuron responds to words denoting slow, gradual diminution or flow—specifically to stems like “trickl-” (trickle, trickling) and “dwindl-” (dwindling).

    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
    ↵↵
    -2.78
            
    -2.66
    </h1>
    -2.39
     they
    -2.19
                
    -2.08
    廰
    -2.06
                                   
    -2.05
    4
    -2.02
                                
    -1.98
    would
    -1.98
    POSITIVE LOGITS
    璆
    2.78
    鴣
    2.66
    ꪔ
    2.56
    龃
    2.56
    𓋼
    2.47
     perlahan
    2.42
    ᕱ
    2.41
    𓆸
    2.36
     ")"
    2.34
    咘
    2.34
    Activations Density 0.003%

    No Known Activations