© 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. 22-GEMMASCOPE-RES-131K
    7. 68574
    Prev
    Next
    INDEX
    Explanations

    Gerhard Berger Formula 1

    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
     at
    -1.66
     in
    -1.66
     while
    -1.51
     which
    -1.50
     when
    -1.48
     so
    -1.46
     will
    -1.45
     did
    -1.42
     by
    -1.40
     as
    -1.34
    POSITIVE LOGITS
     無地
    1.22
    ทั้ง
    1.19
     både
    1.15
     horrid
    1.13
     několika
    1.13
     ENTIRE
    1.09
     cinquième
    1.08
     trozos
    1.08
     méda
    1.08
     récompenses
    1.07
    Activations Density 0.005%

    No Known Activations