© 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. 113449
    Prev
    Next
    INDEX
    Explanations

    Annual General Meeting

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

    annual general meeting and report

    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
     potenc
    0.50
     cuando
    0.48
    парат
    0.47
     diskut
    0.47
    桀
    0.46
     arus
    0.46
     يش
    0.45
     discutir
    0.45
     muestra
    0.44
     макси
    0.44
    POSITIVE LOGITS
    uent
    0.47
    er
    0.45
    ishan
    0.42
    れ
    0.42
    tif
    0.41
    txt
    0.41
     सदैव
    0.41
    //*
    0.40
    ne
    0.40
    akka
    0.40
    Activations Density 0.012%

    No Known Activations