© 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. 1910
    Prev
    Next
    INDEX
    Explanations

    transaction isolation level

    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
    Blue
    -0.73
    asis
    -0.73
     Mädchen
    -0.68
    𝚑
    -0.68
    Software
    -0.67
    Guyana
    -0.66
    bp
    -0.66
    Pen
    -0.65
    mittances
    -0.64
     Blue
    -0.63
    POSITIVE LOGITS
     isolation
    1.52
    Isolation
    1.48
     Isolation
    1.45
    isolation
    1.38
     isol
    1.05
    isol
    1.03
     isolating
    1.00
     Isol
    0.97
     isomorphism
    0.91
    ISOL
    0.90
    Activations Density 0.028%

    No Known Activations