© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16215
    Prev
    Next
    INDEX
    Explanations

    Japanese, English, Chinese particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     which
    -1.77
     and
    -1.70
    ↵
    -1.58
     as
    -1.57
    </h3>
    -1.47
     these
    -1.45
     kunjungan
    -1.41
    the
    -1.38
    That
    -1.37
    nological
    -1.36
    POSITIVE LOGITS
     juſ
    1.66
     améli
    1.62
     signé
    1.51
     katkıda
    1.50
     아니
    1.50
     extremamente
    1.48
     évidemment
    1.47
     graus
    1.45
     mueve
    1.45
    勿論
    1.42
    Activations Density 0.001%

    No Known Activations