© 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. 64223
    Prev
    Next
    INDEX
    Explanations

    Light volume

    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
     підприєм
    -0.82
     Manajemen
    -0.78
    テーマ
    -0.76
     Thema
    -0.73
     Menggunakan
    -0.73
     behövs
    -0.73
     karyawan
    -0.73
     sogar
    -0.72
     Biaya
    -0.72
    晦
    -0.71
    POSITIVE LOGITS
     yet
    0.82
     heavy
    0.80
    Occ
    0.75
    改
    0.73
    ît
    0.72
    Nhi
    0.71
    Wed
    0.71
    ⟹
    0.71
     gede
    0.71
     Dür
    0.70
    Activations Density 0.054%

    No Known Activations