© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112331
    Prev
    Next
    INDEX
    Explanations

    check with family/housemates

    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_31_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
     arquivo
    0.48
     inode
    0.43
     দৃষ্টান্ত
    0.42
     pią
    0.40
     قسم
    0.40
     doxycycline
    0.39
     thả
    0.39
     디
    0.39
     facilité
    0.38
     ocasiones
    0.38
    POSITIVE LOGITS
    Wallet
    0.49
    М
    0.47
    Transaksi
    0.44
    Harga
    0.44
    Hol
    0.43
    Warum
    0.43
    Почему
    0.42
    ByUser
    0.42
    Innen
    0.42
    Мо
    0.42
    Activations Density 0.003%

    No Known Activations