© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95562
    Prev
    Next
    INDEX
    Explanations

    indeed

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

    The neuron activates most strongly on content‐bearing words (i.e. the main nouns, verbs, adjectives, and adverbs) rather than on 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_22/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
     this
    -0.97
     תמיד
    -0.94
     tämän
    -0.94
     zawsze
    -0.88
     Lately
    -0.87
     мод
    -0.83
    都是
    -0.81
     lately
    -0.81
    ֵי
    -0.81
     here
    -0.79
    POSITIVE LOGITS
     indeed
    2.34
    Indeed
    1.54
     Indeed
    1.53
    indeed
    1.52
    果然
    1.49
    確かに
    1.45
     effectivement
    1.42
     действительно
    1.40
     tatsächlich
    1.33
     بالفعل
    1.32
    Activations Density 0.074%

    No Known Activations