© 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. 163572
    Prev
    Next
    INDEX
    Explanations

    Guinness World Record

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

    fundamental way, data coverage, springs square

    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
    軒
    0.54
     اولین
    0.52
    kN
    0.51
    exo
    0.50
    k
    0.50
    ocalypse
    0.48
    o
    0.48
    rias
    0.48
    STRACT
    0.48
    ี
    0.48
    POSITIVE LOGITS
     IncludeField
    0.50
     eluted
    0.45
     reacted
    0.44
     disbursed
    0.43
     ruptured
    0.43
     instigated
    0.43
     penetrated
    0.42
     Seh
    0.41
     Besuch
    0.41
     Dispute
    0.41
    Activations Density 0.000%

    No Known Activations