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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16249
    Prev
    Next
    INDEX
    Explanations

    common phrases and 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
    DataSnapshot
    -1.34
    franco
    -1.23
     their
    -1.23
     you
    -1.20
    ↵↵
    -1.18
    geſ
    -1.16
    𝐒
    -1.16
     They
    -1.13
     regardé
    -1.13
     beheld
    -1.09
    POSITIVE LOGITS
    ஒ
    1.44
    鈊
    1.43
    了一個
    1.41
     kutu
    1.38
    ◆◇
    1.30
    ݮ
    1.29
    
    1.28
    槼
    1.27
     pueda
    1.27
    Ayuda
    1.25
    Activations Density 0.000%

    No Known Activations