© 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. 35979
    Prev
    Next
    INDEX
    Explanations

    http:// or https://

    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
    adhyay
    -1.13
     parece
    -1.13
     his
    -1.11
     escritora
    -1.09
    llten
    -1.08
    )>=
    -1.07
     lavadora
    -1.05
    orul
    -1.04
     família
    -1.03
     estufa
    -1.03
    POSITIVE LOGITS
    jestic
    1.06
     ИН
    1.02
    一方面
    1.00
     téléchargement
    0.98
    Desarrollo
    0.96
     régl
    0.96
     их
    0.96
    比べると
    0.96
     jejich
    0.95
    icordia
    0.94
    Activations Density 0.006%

    No Known Activations