© 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. 25415
    Prev
    Next
    INDEX
    Explanations

    economic performance and conditions

    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
     tertawa
    -1.14
    tellbar
    -1.07
    stoel
    -1.00
    فوائد
    -0.98
     иллюстрация
    -0.98
     gritos
    -0.97
    arreg
    -0.96
     encantado
    -0.94
    Diseño
    -0.93
    gadier
    -0.92
    POSITIVE LOGITS
     growth
    1.22
    enco
    1.02
    ดู
    1.01
    hael
    1.00
     last
    1.00
     its
    0.99
     sector
    0.98
     apesar
    0.96
    のおかげ
    0.96
     September
    0.95
    Activations Density 0.071%

    No Known Activations