© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3452
    Prev
    Next
    INDEX
    Explanations

    list numbering and formatting

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is triggered by mentions of durability or robustness.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    िक
    0.55
    ில்லி
    0.55
    у
    0.55
    ሖ
    0.54
     використа
    0.54
     resultArray
    0.54
    рите
    0.53
     preprocess
    0.53
    𝒆
    0.52
     kernels
    0.50
    POSITIVE LOGITS
     Divers
    0.55
     Pilots
    0.52
    ：《
    0.51
     Veranst
    0.50
     Struggles
    0.50
    oeuvre
    0.50
     Sama
    0.49
     Services
    0.49
    LGBT
    0.49
     Fits
    0.49
    Activations Density 0.000%

    No Known Activations