© 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. 40116
    Prev
    Next
    INDEX
    Explanations

    specific nouns and descriptors

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

    The neuron steadily lights up on content‐bearing nouns—single words naming concrete or abstract “things” or topic concepts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    plural nouns in technical or scientific contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     of
    -1.85
     примерно
    -0.96
     Cs
    -0.95
     अपनी
    -0.94
    ようです
    -0.94
    ())
    -0.93
    คม
    -0.93
     will
    -0.93
     Konferenz
    -0.93
     của
    -0.92
    POSITIVE LOGITS
    したり
    1.20
    が多く
    1.16
     Técnicas
    1.12
    私たちは
    1.12
    ハンドメイド
    1.11
    大佬
    1.09
     Veuillez
    1.09
    knew
    1.09
     Características
    1.05
    あなたは
    1.04
    Activations Density 0.076%

    No Known Activations