© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 18149
    Prev
    Next
    INDEX
    Explanations

    plant vascular system and wood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    罾
    0.45
     المراجعه
    0.43
    ەکە
    0.42
    ستی
    0.41
     dajj
    0.41
     Bead
    0.41
     खे
    0.40
    ベルト
    0.40
    äsident
    0.40
    祸
    0.40
    POSITIVE LOGITS
     xylem
    1.08
     lign
    1.02
     woody
    1.02
     lignin
    1.00
     cellulose
    0.99
     wood
    0.95
     tissues
    0.90
     stems
    0.83
     cellulosic
    0.82
     Cellulose
    0.82
    Activations Density 0.019%

    No Known Activations