© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 83827
    Prev
    Next
    INDEX
    Explanations

    accretion disk

    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
    ΑΣ
    0.50
     печа
    0.39
    τσ
    0.39
    டத்தில்
    0.39
    鍰
    0.38
     dichlor
    0.38
    臤
    0.38
    asem
    0.38
    čet
    0.38
    段
    0.37
    POSITIVE LOGITS
     accretion
    0.74
     disk
    0.62
     disc
    0.61
     accret
    0.58
     discs
    0.56
     inflow
    0.52
     диск
    0.52
     feedings
    0.51
     Disc
    0.50
     feeding
    0.50
    Activations Density 0.008%

    No Known Activations