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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 646
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs or adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </strong>
    -2.66
    D
    -2.05
    T
    -1.96
    K
    -1.91
    ↵
    -1.83
    还想
    -1.72
    残念ながら
    -1.72
     ordinarily
    -1.67
    F
    -1.66
    Who
    -1.62
    POSITIVE LOGITS
     motoru
    1.77
     hossz
    1.73
     stroj
    1.70
    ğına
    1.66
    瘊
    1.63
     decenas
    1.61
     telefonu
    1.59
    k
    1.55
     fapt
    1.55
    tennis
    1.54
    Activations Density 0.021%

    No Known Activations