© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203131
    Prev
    Next
    INDEX
    Explanations

    event, paid, guest, created, largely, absolute, McLaughlin

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining concepts and illustrations

    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_31_width_262k_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
    RegisterClass
    0.44
     altos
    0.43
     আজও
    0.41
     त्यांचा
    0.41
    ᱢ
    0.41
    ंबई
    0.41
     سبق
    0.41
    तूल
    0.40
     Stu
    0.40
     cathodes
    0.40
    POSITIVE LOGITS
    用户
    0.52
    ne
    0.49
    ◕
    0.46
     cena
    0.46
     eye
    0.45
     tam
    0.45
     पुन
    0.45
    神器
    0.45
    ListItem
    0.44
     PRINT
    0.44
    Activations Density 0.000%

    No Known Activations