© 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. 53979
    Prev
    Next
    INDEX
    Explanations

    platform rules moderation

    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
    atoshi
    -0.82
    étiques
    -0.82
    (_.
    -0.81
     unconditional
    -0.79
    атра
    -0.77
    USB
    -0.77
    ătate
    -0.77
    scalatest
    -0.75
     formales
    -0.75
    нах
    -0.75
    POSITIVE LOGITS
     algorithms
    1.38
     moderation
    1.35
     users
    1.30
     user
    1.30
     algorithm
    1.26
     platform
    1.19
     алгорит
    1.17
     Algorithm
    1.16
     algorithmic
    1.14
     platforms
    1.13
    Activations Density 0.024%

    No Known Activations