© 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. 63473
    Prev
    Next
    INDEX
    Explanations

    plane crash

    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
    detectChanges
    -0.88
    𝑉
    -0.82
    opardy
    -0.82
     BytesLike
    -0.77
    ImageBackground
    -0.76
    жливо
    -0.74
     Drivers
    -0.74
    ingang
    -0.72
     déplacer
    -0.72
    匍
    -0.71
    POSITIVE LOGITS
     crash
    3.58
     crashed
    2.97
    crash
    2.88
     crashes
    2.84
    Crash
    2.63
     Crash
    2.44
     crashing
    2.22
    cras
    2.20
     Cras
    1.90
     wreckage
    1.72
    Activations Density 0.035%

    No Known Activations