© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 2976
    Prev
    Next
    INDEX
    Explanations

    descriptive nouns and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
    Х
    0.67
     $^{
    0.65
    следование
    0.64
    $^{
    0.62
    フォ
    0.60
     Х
    0.59
    。
    0.58
    ->
    0.58
    𝑜
    0.58
    égi
    0.57
    POSITIVE LOGITS
     nestled
    0.80
     strife
    0.78
     통한
    0.77
     growing
    0.77
     tales
    0.77
     lindo
    0.76
     proudly
    0.74
    ில்லி
    0.73
     gates
    0.73
     angst
    0.73
    Activations Density 0.238%

    No Known Activations