© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30762
    Prev
    Next
    INDEX
    Explanations

    fats and oils

    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_31_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
    闿
    0.46
     Giveen
    0.45
     uranyl
    0.45
     노래
    0.45
     Dye
    0.44
     Ичиго
    0.42
     primaryLanguage
    0.42
    шымта
    0.41
    𝙵
    0.41
     साइंस
    0.41
    POSITIVE LOGITS
     oil
    1.17
    油
    1.09
     oils
    1.06
     minyak
    1.05
     Oil
    1.03
    オイル
    1.03
    Oil
    1.02
    huile
    0.99
    oil
    0.98
     óleo
    0.96
    Activations Density 0.129%

    No Known Activations