© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35135
    Prev
    Next
    INDEX
    Explanations

    pickles and pickling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    チョコレート
    0.44
    Chocolate
    0.43
    coco
    0.42
    Coco
    0.41
     Cocoa
    0.39
    牛乳
    0.39
    🍫
    0.39
    邰
    0.39
    Gran
    0.39
     Latte
    0.39
    POSITIVE LOGITS
     pickle
    1.34
     pickled
    1.28
     pickles
    1.28
    pickle
    1.15
     Pickle
    1.05
    醃
    1.05
    腌
    1.02
     brine
    0.98
    漬
    0.91
     अचार
    0.88
    Activations Density 0.021%

    No Known Activations