© 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. 48789
    Prev
    Next
    INDEX
    Explanations

    orders lifted

    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
    菓子
    -0.83
    }\|
    -0.78
     Kirchner
    -0.76
    resize
    -0.76
     kue
    -0.75
     Sully
    -0.75
     empate
    -0.75
     blom
    -0.74
     закры
    -0.74
     shuts
    -0.73
    POSITIVE LOGITS
     lifting
    4.44
     lifted
    4.13
     lift
    3.75
    Lifting
    3.55
     lifts
    3.47
     Lifting
    3.44
    lifting
    3.33
     Lift
    3.23
    lift
    3.02
    lifted
    3.02
    Activations Density 0.120%

    No Known Activations