© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1161
    Prev
    Next
    INDEX
    Explanations

    Marriott, Vacation Club, Quality control

    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
     كره
    -0.75
     :*
    -0.75
     broder
    -0.74
    Karina
    -0.73
     😘
    -0.73
    Identific
    -0.72
    
    -0.72
     bandung
    -0.71
     Sekret
    -0.71
     Energi
    -0.70
    POSITIVE LOGITS
     Marriott
    1.15
    流
    0.85
    flu
    0.85
     sci
    0.80
    Mar
    0.80
     replace
    0.79
    landi
    0.75
     Hollow
    0.74
    Loire
    0.73
    نا
    0.73
    Activations Density 0.016%

    No Known Activations