© 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-65K
    7. 35753
    Prev
    Next
    INDEX
    Explanations

    price ceilings; luggage; vapor pressure

    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_65k_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
    ethnic
    0.46
    response
    0.43
    peace
    0.43
    io
    0.41
     \
    0.41
    pes
    0.40
     response
    0.38
     Flyer
    0.38
    actions
    0.38
    development
    0.38
    POSITIVE LOGITS
    Penumpang
    0.45
    CHU
    0.45
    supportsFocus
    0.44
     смерти
    0.43
    ]，
    0.42
     بوابة
    0.41
    व्यापी
    0.41
     fodder
    0.41
     staples
    0.41
     defra
    0.40
    Activations Density 0.008%

    No Known Activations