© 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. 130857
    Prev
    Next
    INDEX
    Explanations

    intentional actions or states

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

    The neuron activates on occurrences of the root “intentional,” i.e. words containing “intentional.”

    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
     представители
    -2.63
    廕
    -2.58
    各样的
    -2.58
    鬭
    -2.53
     Your
    -2.38
    ￪
    -2.33
     increíbles
    -2.31
    詎
    -2.30
    嵙
    -2.23
    𞤮
    -2.20
    POSITIVE LOGITS
    1
    3.03
    ization
    2.66
    ist
    2.59
    .
    2.53
    
    2.47
    犇
    2.42
    する
    2.36
    猹
    2.33
     \&
    2.28
     That
    2.22
    Activations Density 0.004%

    No Known Activations