© 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. 10-GEMMASCOPE-RES-131K
    7. 72543
    Prev
    Next
    INDEX
    Explanations

    CSF

    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
    昻
    -2.83
            
    -2.80
     =
    -2.64
     intricacies
    -2.55
    鸲
    -2.50
        
    -2.45
     touted
    -2.44
    可能な
    -2.42
    ných
    -2.41
     dasarnya
    -2.33
    POSITIVE LOGITS
    枼
    2.91
     gewo
    2.59
    垆
    2.56
     dieß
    2.47
    Ꮿ
    2.38
     absolut
    2.36
     competi
    2.34
    捽
    2.33
    鬭
    2.31
    栳
    2.30
    Activations Density 0.005%

    No Known Activations