© 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. 66729
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
     of
    -1.11
     same
    -1.07
    ⅔
    -0.99
    Уже
    -0.96
     all
    -0.88
    🤝
    -0.87
     find
    -0.87
     cũng
    -0.86
     still
    -0.85
     start
    -0.85
    POSITIVE LOGITS
     dobrý
    1.25
     srdce
    1.15
     няколко
    1.11
     cantantes
    1.08
     dobré
    1.08
     тук
    1.05
     потім
    1.02
     různ
    1.02
     dře
    1.01
     šť
    1.00
    Activations Density 0.150%

    No Known Activations