© 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. 22-GEMMASCOPE-RES-131K
    7. 65236
    Prev
    Next
    INDEX
    Explanations

    integer arrays and data structures

    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_22/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
     Mú
    -1.09
     herself
    -1.05
    ioterapia
    -1.02
    ༷
    -1.02
     coloridos
    -1.01
    Ꮸ
    -0.99
    scut
    -0.98
    cubo
    -0.98
    Execute
    -0.97
    Thi
    -0.97
    POSITIVE LOGITS
     zijn
    1.15
    meteries
    1.13
     himself
    1.12
     is
    1.12
    使其
    1.09
     polizia
    1.04
    甚至是
    1.04
    вшего
    1.04
     kaas
    1.04
    」，
    1.03
    Activations Density 0.012%

    No Known Activations