© 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. 75588
    Prev
    Next
    INDEX
    Explanations

    names and initials

    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
    P
    -1.30
    B
    -1.27
     That
    -1.24
     get
    -1.23
    K
    -1.23
          
    -1.21
     and
    -1.19
     Despite
    -1.18
    M
    -1.18
    R
    -1.17
    POSITIVE LOGITS
     bluz
    1.50
     camiset
    1.45
     pistolet
    1.41
     gré
    1.38
     slike
    1.36
     Atención
    1.33
     père
    1.32
    謦
    1.30
     tunik
    1.30
     sava
    1.30
    Activations Density 0.362%

    No Known Activations