© 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. 118824
    Prev
    Next
    INDEX
    Explanations

    access your

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

    The main thing this neuron does is detect semantically salient content words—especially proper nouns, technical terms, and other topic-specific vocabulary.

    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
     their
    -1.58
    Mereka
    -1.43
     they
    -1.42
     jejich
    -1.42
     -
    -1.34
    g
    -1.32
     leur
    -1.31
     swojej
    -1.31
     swoim
    -1.30
    常见的
    -1.30
    POSITIVE LOGITS
    lamabad
    1.45
    iress
    1.41
     another
    1.41
     again
    1.38
    atient
    1.34
    /");
    1.27
    waits
    1.27
     tla
    1.27
     itself
    1.27
     gedeelte
    1.27
    Activations Density 0.183%

    No Known Activations