© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49848
    Prev
    Next
    INDEX
    Explanations

    food intake and meals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
    CTest
    0.39
    JX
    0.38
     Prado
    0.38
     respected
    0.36
    বৃদ্ধি
    0.36
     delayed
    0.35
    ოში
    0.35
    笤
    0.35
    মহ
    0.35
    avamo
    0.34
    POSITIVE LOGITS
     soups
    0.48
     salads
    0.45
    กิน
    0.44
     Eat
    0.43
     bouillon
    0.43
    솥
    0.42
    breakfast
    0.41
     먹
    0.40
    早餐
    0.40
    食べた
    0.40
    Activations Density 0.013%

    No Known Activations