© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64472
    Prev
    Next
    INDEX
    Explanations

    a, an, one, or similar

    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
     seleccionadas
    -1.44
     těch
    -1.38
     HÀ
    -1.36
     самых
    -1.31
     moft
    -1.30
     tdci
    -1.29
    grees
    -1.28
     различни
    -1.24
     definida
    -1.23
     seleccionados
    -1.23
    POSITIVE LOGITS
     a
    5.69
     an
    3.56
     one
    2.69
     एक
    1.98
     একটি
    1.90
     another
    1.73
     among
    1.73
     أحد
    1.66
    一个
    1.65
     một
    1.61
    Activations Density 0.202%

    No Known Activations