© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57001
    Prev
    Next
    INDEX
    Explanations

    company and product names

    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
     one
    -1.06
     as
    -1.05
     In
    -1.02
     With
    -1.01
     K
    -0.99
     Since
    -0.98
     Like
    -0.96
     m
    -0.94
     While
    -0.94
     enhancing
    -0.94
    POSITIVE LOGITS
    Semua
    1.29
    襌
    1.28
     seksi
    1.27
    Penulis
    1.24
     éx
    1.23
    慙
    1.22
    Sudah
    1.20
    饜
    1.19
     incrí
    1.17
    Màu
    1.17
    Activations Density 0.149%

    No Known Activations