© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47934
    Prev
    Next
    INDEX
    Explanations

    Maximus and maxima values

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

    The neuron activates on words containing the root “maxim,” such as “Maximus,” “maxima,” and “minima.”

    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
    料
    -2.48
    沨
    -2.25
    
    -2.25
    vidéo
    -2.25
     ^_^
    -2.22
    “
    -2.20
    vidla
    -2.16
    quatre
    -2.11
     becas
    -2.11
    POSITIVE LOGITS
     أن
    2.69
    2.61
     que
    2.61
     })}
    2.41
     возможно
    2.39
    },[])
    2.31
    ());
    2.30
    2.28
     даже
    2.27
    ーーー
    2.27
    Activations Density 0.004%

    No Known Activations