© 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. 48601
    Prev
    Next
    INDEX
    Explanations

    20

    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
     methodName
    -0.77
    derna
    -0.75
     framework
    -0.75
    fem
    -0.70
    etzten
    -0.69
    واد
    -0.69
    zeugung
    -0.68
     fonctionnalité
    -0.67
    CLIN
    -0.66
    ictus
    -0.66
    POSITIVE LOGITS
    oll
    0.77
     sub
    0.75
     callable
    0.75
    camore
    0.75
     IDA
    0.74
     Trapp
    0.73
     PIL
    0.73
    ysen
    0.73
     thuis
    0.71
     IOS
    0.71
    Activations Density 0.010%

    No Known Activations