© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38482
    Prev
    Next
    INDEX
    Explanations

    names and code keywords

    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
     
    -1.53
     llego
    -0.99
    免許
    -0.97
     זיי
    -0.94
    Dá
    -0.91
    Encu
    -0.89
    – 
    -0.88
     when
    -0.88
     what
    -0.87
    ologische
    -0.87
    POSITIVE LOGITS
    ləş
    1.27
    ierać
    1.27
     魂
    1.16
     empleos
    1.09
     harika
    1.09
    tualmente
    1.09
    呶
    1.09
     lieto
    1.08
     हालांकि
    1.08
    felizmente
    1.08
    Activations Density 0.001%

    No Known Activations