© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 92921
    Prev
    Next
    INDEX
    Explanations

    introductions and section titles

    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
     should
    -1.16
     at
    -1.01
     from
    -0.98
     simbol
    -0.94
     because
    -0.94
     vatt
    -0.94
     difficulties
    -0.93
     laik
    -0.91
     君
    -0.91
     on
    -0.91
    POSITIVE LOGITS
    newpage
    1.07
     gestes
    1.02
     acordo
    0.96
    ouro
    0.91
     sembler
    0.89
    と同じ
    0.88
     mettent
    0.88
     dilapidated
    0.88
     Vám
    0.87
     remercier
    0.87
    Activations Density 0.000%

    No Known Activations