© 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. 84822
    Prev
    Next
    INDEX
    Explanations

    viagra, priligy, replica rolex

    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
    cestors
    -1.27
     BRID
    -0.96
    tismo
    -0.95
    archical
    -0.94
     Truths
    -0.91
    ματος
    -0.87
    американ
    -0.87
     COUNTRIES
    -0.86
    🫃
    -0.85
    СТА
    -0.85
    POSITIVE LOGITS
    為に
    0.95
    失踪
    0.90
    管家
    0.90
    されており
    0.89
    ##############
    0.89
    綺麗に
    0.88
    二十四
    0.88
    安徽
    0.88
    Vapour
    0.87
    中略
    0.85
    Activations Density 0.010%

    No Known Activations