© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77141
    Prev
    Next
    INDEX
    Explanations

    common internet phrases

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

    The neuron fires on content‐bearing words (nouns, verbs, adjectives, proper names, etc.) 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_34/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
    crazy
    -1.06
    🙈
    -0.96
    ykite
    -0.96
     Letras
    -0.95
    Modificar
    -0.94
     Inglés
    -0.92
     hafta
    -0.90
     assholes
    -0.90
    Docs
    -0.90
     Arquitectura
    -0.90
    POSITIVE LOGITS
     wholesome
    1.26
     memes
    1.16
    olesome
    1.15
     gay
    1.10
     cringe
    1.10
    おわりに
    1.09
    bois
    1.09
    ඩ
    1.07
     kayna
    1.06
     hoe
    1.04
    Activations Density 0.064%

    No Known Activations