© 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. 1894
    Prev
    Next
    INDEX
    Explanations

    quantum density matrices and states

    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
     ਹ
    -0.96
    ఔ
    -0.89
     bureauc
    -0.79
     DBA
    -0.78
     bae
    -0.73
     SWAT
    -0.73
     nomads
    -0.72
    èvres
    -0.72
    alow
    -0.72
     Tula
    -0.72
    POSITIVE LOGITS
    rho
    0.92
     Lind
    0.88
     deco
    0.81
     pureza
    0.81
     rho
    0.81
     trace
    0.80
     mixed
    0.80
     Bren
    0.79
     Kraus
    0.79
     thermal
    0.79
    Activations Density 0.048%

    No Known Activations