© 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. 15298
    Prev
    Next
    INDEX
    Explanations

    finally concluding

    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
     pierws
    -1.23
    начала
    -1.09
    先是
    -1.09
     первых
    -1.08
     início
    -1.05
    usually
    -1.04
    まず
    -1.02
     особенно
    -1.01
     ersten
    -1.01
    description
    -1.01
    POSITIVE LOGITS
     further
    1.55
     final
    1.41
     another
    1.36
     concluding
    1.30
     conclusion
    1.30
    ต่อไป
    1.27
     concludes
    1.23
     finally
    1.21
    Lastly
    1.20
     concluded
    1.18
    Activations Density 0.003%

    No Known Activations