© 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. 41-GEMMASCOPE-2-RES-262K
    7. 7843
    Prev
    Next
    INDEX
    Explanations

    vegetable oil

    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_all/layer_41_width_262k_l0_big
    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
    wavelength
    0.52
    ឹម
    0.50
    និច
    0.48
    袜
    0.48
    AlignedText
    0.48
     perturbations
    0.47
     compactness
    0.47
    閾
    0.46
     symptômes
    0.46
    ৃঙ্খলা
    0.46
    POSITIVE LOGITS
     oil
    1.91
     oils
    1.88
     Oils
    1.88
     Oil
    1.76
    Oil
    1.71
    油
    1.68
     तेल
    1.62
     масла
    1.61
     기름
    1.52
    oil
    1.49
    Activations Density 0.043%

    No Known Activations