© 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-RES-262K
    7. 23310
    Prev
    Next
    INDEX
    Explanations

    high in calories, fat, sugar

    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
    胜
    0.53
    Artista
    0.47
    饰
    0.43
    DetailPage
    0.43
    rato
    0.43
    队的
    0.43
    诤
    0.43
    Puede
    0.43
    marked
    0.42
    win
    0.42
    POSITIVE LOGITS
     s
    0.57
     roupa
    0.53
     Romania
    0.50
     toil
    0.50
     ancak
    0.48
     apet
    0.48
     ă
    0.47
     caloric
    0.47
     aerosols
    0.46
     gas
    0.46
    Activations Density 0.004%

    No Known Activations