© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106387
    Prev
    Next
    INDEX
    Explanations

    alarm severity

    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
    Negative Logits
     Kain
    -0.81
     Romagna
    -0.72
    LF
    -0.71
    諒
    -0.69
     abyss
    -0.69
     vícti
    -0.68
     captives
    -0.68
    Erica
    -0.67
     corneal
    -0.66
     DVD
    -0.66
    POSITIVE LOGITS
     PV
    0.99
    pv
    0.88
    PV
    0.88
     pv
    0.81
     epics
    0.77
    severe
    0.77
    ioc
    0.76
    alarm
    0.75
    severity
    0.74
     enfri
    0.74
    Activations Density 0.006%

    No Known Activations