© 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. 117581
    Prev
    Next
    INDEX
    Explanations

    names followed by surname or descriptor

    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
    Probably
    -0.79
     головы
    -0.78
     déclare
    -0.77
     equipada
    -0.74
    Lokasi
    -0.73
     refugi
    -0.73
     Geschw
    -0.73
    ায়
    -0.71
     equipado
    -0.71
    волю
    -0.70
    POSITIVE LOGITS
    DMSO
    1.05
    oczes
    1.04
     faptul
    0.97
    tuce
    0.97
     lijst
    0.95
    outine
    0.95
    ipedi
    0.94
    ఞ
    0.94
     intervening
    0.93
     educação
    0.93
    Activations Density 0.051%

    No Known Activations