© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5609
    Prev
    Next
    INDEX
    Explanations

    binary operations and memory

    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_17_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
     Phương
    0.78
     dashboard
    0.76
    測
    0.74
     dashboards
    0.72
     meteor
    0.72
     anhyd
    0.72
    Aur
    0.72
     phylogenetic
    0.72
     ಥ
    0.71
     matplotlib
    0.70
    POSITIVE LOGITS
     memory
    0.95
     Memory
    0.94
    Memory
    0.84
     memories
    0.82
    memory
    0.78
     operand
    0.77
     memória
    0.77
     memoria
    0.76
     Memories
    0.75
     opcode
    0.71
    Activations Density 0.900%

    No Known Activations