© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55605
    Prev
    Next
    INDEX
    Explanations

    operational units

    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
     matrix
    -0.84
     MATRIX
    -0.75
    matrix
    -0.73
     gentleman
    -0.73
    MATRIX
    -0.70
    pmatrix
    -0.68
    ablen
    -0.68
     PROTEIN
    -0.67
     خوا
    -0.66
     Matrix
    -0.66
    POSITIVE LOGITS
     invader
    0.73
     wichtiger
    0.71
    Inspection
    0.67
    Mk
    0.66
     Renewable
    0.66
    лық
    0.65
     dankbar
    0.65
     tsar
    0.64
     FTSE
    0.64
    acq
    0.64
    Activations Density 0.058%

    No Known Activations