© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12953
    Prev
    Next
    INDEX
    Explanations

    differentiate from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    1.08
     etc
    0.93
     е
    0.92
     "
    0.92
    -
    0.91
     а
    0.90
    jug
    0.90
     =
    0.90
    /
    0.89
     +
    0.89
    POSITIVE LOGITS
     leveraging
    2.35
     policymakers
    2.32
     benchmarking
    2.23
     resilience
    2.19
     perspectivas
    2.19
     optimism
    2.19
     stakeholders
    2.18
     renewables
    2.18
     benchmarks
    2.17
     overarching
    2.11
    Activations Density 0.268%

    No Known Activations