© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34019
    Prev
    Next
    INDEX
    Explanations

    last, first, next

    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_22/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
     både
    -1.00
    both
    -0.90
     both
    -0.85
    ⅙
    -0.82
     båda
    -0.82
     часть
    -0.81
    kirch
    -0.81
    anel
    -0.80
     milyen
    -0.80
     tambien
    -0.80
    POSITIVE LOGITS
     last
    2.06
     first
    1.57
     terakhir
    1.37
     next
    1.26
     posled
    1.25
     cuối
    1.20
     último
    1.18
     latest
    1.16
     послед
    1.15
     ensimmä
    1.13
    Activations Density 0.118%

    No Known Activations