© 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. 22-GEMMASCOPE-RES-131K
    7. 98632
    Prev
    Next
    INDEX
    Explanations

    improving oneself and life

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

    The neuron fires on semantically important content words (key nouns, verbs, and adjectives) rather than on 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_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
     if
    -1.50
     perquè
    -1.27
     leurs
    -1.24
     their
    -1.23
     cotidiana
    -1.20
     mereka
    -1.16
    他们在
    -1.13
     are
    -1.12
    Their
    -1.12
     nuestras
    -1.11
    POSITIVE LOGITS
     improved
    1.45
     life
    1.40
     everything
    1.35
    ystemet
    1.34
     wasn
    1.30
     things
    1.30
     changed
    1.30
     eventually
    1.30
    máy
    1.27
    ᚠ
    1.27
    Activations Density 0.022%

    No Known Activations