© 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. 107
    Prev
    Next
    INDEX
    Explanations

    career beginnings and education

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

    The neuron fires strongly on content-bearing, topic-specific words (nouns, verbs, 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
     now
    -1.16
     new
    -1.14
    ཟ
    -1.13
     on
    -1.04
     that
    -1.03
     again
    -1.01
    new
    -1.00
    ิส
    -0.98
    일에
    -0.98
    ili
    -0.97
    POSITIVE LOGITS
     écoute
    1.17
     sereia
    1.09
     berço
    1.05
     USSR
    1.05
     Grèce
    1.04
     Antes
    1.03
     Accueil
    1.01
    częściej
    0.99
     PUEDE
    0.98
    に近い
    0.97
    Activations Density 0.119%

    No Known Activations