© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78017
    Prev
    Next
    INDEX
    Explanations

    married at first sight

    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
     notes
    -0.77
    競
    -0.72
    厘
    -0.71
    ActionEvent
    -0.71
     sequins
    -0.71
    ậm
    -0.68
     maternal
    -0.66
     exuberant
    -0.66
    ौर
    -0.65
    manchester
    -0.65
    POSITIVE LOGITS
     matched
    1.15
     experiment
    1.13
     eksper
    1.10
     experts
    1.09
     matchmaking
    1.08
     couples
    1.02
    experts
    1.00
    Experts
    0.96
    experiment
    0.95
    matched
    0.93
    Activations Density 0.003%

    No Known Activations