© 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. 22-GEMMASCOPE-RES-131K
    7. 34845
    Prev
    Next
    INDEX
    Explanations

    leading professional

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

    The neuron fires on positive promotional adjectives and superlative descriptors used to praise or market a product or service.

    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
    inerario
    -1.47
     beroep
    -1.47
     üblichen
    -1.40
     gemeenten
    -1.40
     moż
    -1.31
    の基本
    -1.31
    ícias
    -1.27
     risico
    -1.27
     activiteiten
    -1.26
     vrijwilli
    -1.24
    POSITIVE LOGITS
    Ė
    1.34
    توضیحات
    1.25
     ligt
    1.14
    咐
    1.05
     برگزار
    1.04
     свою
    1.04
     Ihe
    1.04
    嘉宾
    1.04
     מִ
    1.01
    ﾚ
    1.01
    Activations Density 0.170%

    No Known Activations