© 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. 48440
    Prev
    Next
    INDEX
    Explanations

    process and future concepts

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

    The neuron selectively responds to content–bearing words (especially longer, domain-specific or informational nouns and verbs), while ignoring common function words.

    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
     –
    -1.83
     or
    -1.73
    y
    -1.54
     in
    -1.52
    /
    -1.51
    i
    -1.48
     -
    -1.44
     allow
    -1.42
    ?
    -1.38
    ”
    -1.36
    POSITIVE LOGITS
     maska
    1.51
    IZES
    1.48
    tych
    1.48
     asist
    1.48
     dini
    1.46
     kafe
    1.46
     misi
    1.45
    usions
    1.44
    )),
    1.43
    .《
    1.43
    Activations Density 0.175%

    No Known Activations