© 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. 57822
    Prev
    Next
    INDEX
    Explanations

    MICR line checks banking

    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
     biomass
    -0.74
     Asbestos
    -0.73
     leases
    -0.73
     lease
    -0.71
    Literary
    -0.70
    Sapphire
    -0.70
    ící
    -0.69
     Biomass
    -0.69
    残り
    -0.68
     rappers
    -0.67
    POSITIVE LOGITS
     dishon
    1.20
     drawer
    1.19
     Drawer
    1.07
     drawers
    1.02
    Drawer
    1.02
     honoring
    1.01
    Dra
    0.99
    Presentation
    0.96
     collection
    0.93
     banking
    0.93
    Activations Density 0.015%

    No Known Activations