© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11605
    Prev
    Next
    INDEX
    Explanations

    current frontrunner champion

    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
    Not in Any Lists

    No Comments

    Negative Logits
    amazing
    1.40
    universe
    1.37
    f
    1.33
    tx
    1.29
    um
    1.28
    if
    1.27
    instit
    1.26
    cmd
    1.26
    u
    1.25
    ulik
    1.24
    POSITIVE LOGITS
     pedal
    1.50
     亠
    1.44
     addCriterion
    1.40
     dieci
    1.39
     skating
    1.37
    IdleSync
    1.36
     некоторое
    1.36
     nė
    1.36
     좀
    1.34
     taxi
    1.33
    Activations Density 0.000%

    No Known Activations