© 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. 103570
    Prev
    Next
    INDEX
    Explanations

    code configuration options

    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
     your
    -1.77
     you
    -1.29
    病人
    -1.08
     bezig
    -1.05
     gustó
    -1.00
     on
    -0.99
     so
    -0.99
     balcón
    -0.99
    ać
    -0.98
     had
    -0.94
    POSITIVE LOGITS
     Undang
    1.19
     sorella
    1.13
     polizia
    1.12
     debilit
    1.09
    `
    1.06
    rizona
    1.05
     considérons
    1.05
     Mexique
    1.04
     vín
    1.04
     ceux
    1.04
    Activations Density 0.074%

    No Known Activations