© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 626
    Prev
    Next
    INDEX
    Explanations

    prepare and execute database queries

    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_10/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
    哽
    -1.29
    łem
    -1.29
    Literat
    -1.20
    père
    -1.15
    Additional
    -1.13
    Standort
    -1.13
     chiama
    -1.09
    [];
    -1.08
    ridged
    -1.08
    </h3>
    -1.08
    POSITIVE LOGITS
     has
    1.52
     as
    1.28
     of
    1.28
     about
    1.21
     aimed
    1.10
    os
    1.09
     without
    1.09
    berikut
    1.06
    няются
    1.06
      
    1.05
    Activations Density 0.084%

    No Known Activations