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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93996
    Prev
    Next
    INDEX
    Explanations

    all is well

    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_34/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
     rembourse
    -1.07
     améli
    -0.98
    ggable
    -0.94
    kann
    -0.92
    couldn
    -0.91
    LÄ
    -0.89
    doesn
    -0.88
    بدون
    -0.88
    strukturen
    -0.87
     récol
    -0.86
    POSITIVE LOGITS
     well
    1.88
     okay
    1.48
     fine
    1.44
     OK
    1.41
     ok
    1.34
     as
    1.34
     Okay
    1.30
     alright
    1.27
     порядке
    1.26
     good
    1.23
    Activations Density 0.020%

    No Known Activations