© 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. 31669
    Prev
    Next
    INDEX
    Explanations

    URLs, questions, lists

    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
    LORD
    -0.81
     televised
    -0.76
     mahal
    -0.76
     tulle
    -0.75
    slice
    -0.75
     Eau
    -0.75
     Presenter
    -0.75
     workbook
    -0.75
     }_{
    -0.74
     Irma
    -0.73
    POSITIVE LOGITS
     Commission
    0.74
     Edit
    0.73
     algo
    0.71
     financeira
    0.71
    ighters
    0.71
    algo
    0.71
     sidebar
    0.70
     Polak
    0.69
    uously
    0.68
    呦
    0.68
    Activations Density 0.062%

    No Known Activations