© 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. 93501
    Prev
    Next
    INDEX
    Explanations

    X is Y

    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
     neemt
    -1.26
     coû
    -1.19
     obuv
    -1.17
     hogyan
    -1.16
    mands
    -1.15
     refroid
    -1.14
     sağlar
    -1.14
    cego
    -1.14
     dificultades
    -1.13
     fronteras
    -1.13
    POSITIVE LOGITS
     is
    4.69
     was
    3.06
     are
    2.48
     for
    2.45
     είναι
    2.27
     would
    2.17
    的是
    2.03
    คือ
    1.98
     in
    1.90
     является
    1.86
    Activations Density 0.098%

    No Known Activations