© 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. 26242
    Prev
    Next
    INDEX
    Explanations

    educational institutions

    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
     it
    -1.20
     already
    -1.19
     fiecare
    -0.94
    已
    -0.92
     ormai
    -0.90
    已經
    -0.89
    も行
    -0.89
     cómodo
    -0.89
     each
    -0.88
    ڻ
    -0.88
    POSITIVE LOGITS
    <>());
    1.22
    strando
    1.11
    鉛筆
    1.11
    eventually
    1.10
    uliert
    1.09
    谥
    1.05
    鎧
    1.05
    annels
    1.04
    OrNil
    1.04
     olarak
    1.02
    Activations Density 0.060%

    No Known Activations