© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5466
    Prev
    Next
    INDEX
    Explanations

    Polish, Romanian, Hungarian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tightly
    0.85
     너
    0.77
    టానికి
    0.73
     classed
    0.72
     되
    0.71
    ди
    0.69
    塑
    0.67
    безпе
    0.67
     에
    0.66
     Day
    0.66
    POSITIVE LOGITS
     totale
    0.96
     realizar
    0.93
     realização
    0.89
     dez
    0.87
     casa
    0.86
     în
    0.86
     este
    0.83
     terminar
    0.83
     creer
    0.82
     transmis
    0.81
    Activations Density 0.047%

    No Known Activations