© 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. 34-GEMMASCOPE-RES-131K
    7. 109481
    Prev
    Next
    INDEX
    Explanations

    surnames

    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
     These
    -1.48
     Each
    -1.45
     While
    -1.31
    為に
    -1.29
     Both
    -1.27
     різних
    -1.27
     Aside
    -1.24
     Different
    -1.23
     azonban
    -1.22
    With
    -1.18
    POSITIVE LOGITS
     RÉ
    1.49
     remé
    1.48
     naran
    1.45
     accepte
    1.40
     vermel
    1.38
     organik
    1.38
     haj
    1.37
     centrum
    1.34
     fó
    1.34
     fré
    1.34
    Activations Density 0.140%

    No Known Activations