© 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. 117628
    Prev
    Next
    INDEX
    Explanations

    multiple processors, cores, instances

    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
     that
    -1.04
    dados
    -0.93
     pomocou
    -0.93
    日子
    -0.89
    那些
    -0.88
     Nelson
    -0.86
    枱
    -0.85
    atoms
    -0.84
    始めた
    -0.84
     devem
    -0.84
    POSITIVE LOGITS
     different
    2.39
     separate
    2.27
     seperate
    1.89
     simultaneous
    1.86
    separate
    1.69
     gleichzeitig
    1.62
     identical
    1.57
    different
    1.55
     différents
    1.54
    simult
    1.53
    Activations Density 0.213%

    No Known Activations