Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 178
    Prev
    Next
    INDEX
    Explanations

    bodily organs and hormones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﺪ
    0.34
    ﻄ
    0.32
    ного
    0.30
    ası
    0.30
    です
    0.30
    f
    0.29
    évolution
    0.28
    v
    0.28
    лет
    0.28
    лин
    0.28
    POSITIVE LOGITS
    ↵
    0.54
     be
    0.42
            
    0.40
     cells
    0.39
     muscles
    0.38
     neurons
    0.37
     AMPK
    0.36
     for
    0.35
     arteries
    0.35
     proteins
    0.35
    Activations Density 1.239%

    No Known Activations