© 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. 34-GEMMASCOPE-RES-131K
    7. 31354
    Prev
    Next
    INDEX
    Explanations

    if isset or defined

    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_34/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
    glicher
    -0.96
    〜！
    -0.94
     disesuaikan
    -0.93
     fácil
    -0.86
     arrivée
    -0.84
    schwar
    -0.83
    チュラル
    -0.82
     memanggil
    -0.82
    ável
    -0.80
     if
    -0.78
    POSITIVE LOGITS
     and
    1.18
     justru
    0.90
    mills
    0.88
    grès
    0.85
    譯
    0.82
     кино
    0.82
     $
    0.81
     bowiem
    0.81
    atoma
    0.81
    lovakia
    0.81
    Activations Density 0.004%

    No Known Activations