© 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. 118318
    Prev
    Next
    INDEX
    Explanations

    potential to reveal or help

    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
     exemples
    -0.90
    @(
    -0.88
    
    -0.87
     positif
    -0.85
     ANGEL
    -0.79
    čki
    -0.79
    calculated
    -0.78
    Ix
    -0.78
    +"_
    -0.78
    klaim
    -0.77
    POSITIVE LOGITS
     revealing
    3.20
     reveal
    3.03
     reveals
    2.88
     help
    2.78
     clues
    2.64
     helps
    2.63
     provide
    2.45
     tells
    2.44
     clue
    2.33
     helpful
    2.31
    Activations Density 0.253%

    No Known Activations