© 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. 63093
    Prev
    Next
    INDEX
    Explanations

    case numbers and court documents

    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
     UUID
    -1.03
    Ainda
    -0.86
    sko
    -0.85
    lators
    -0.85
    шти
    -0.84
     AND
    -0.76
    exus
    -0.75
    如下图
    -0.75
     timers
    -0.75
     timedelta
    -0.74
    POSITIVE LOGITS
     printing
    1.18
     Printed
    1.09
     printed
    1.02
    Printed
    1.01
    Revised
    0.96
    打印
    0.96
    attamento
    0.96
     revised
    0.93
     Printing
    0.92
     даже
    0.91
    Activations Density 0.085%

    No Known Activations