© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11207
    Prev
    Next
    INDEX
    Explanations

    direct effect or result

    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_10/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
     a
    -1.84
     {
    -1.77
    ("
    -1.76
     în
    -1.64
    возмо
    -1.61
     –
    -1.52
    datable
    -1.50
    шая
    -1.49
    isait
    -1.48
    otriz
    -1.45
    POSITIVE LOGITS
     and
    1.78
     udało
    1.77
     poliuret
    1.73
    ㍉
    1.71
     nuest
    1.70
     bezpośrednio
    1.70
    Ꮉ
    1.67
     gezet
    1.66
     portatil
    1.63
     både
    1.62
    Activations Density 0.027%

    No Known Activations