© 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. 16-GEMMASCOPE-2-RES-262K
    7. 14589
    Prev
    Next
    INDEX
    Explanations

    junit tests

    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_16_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
    1.95
     can
    1.31
    c
    1.18
    F
    1.18
    Y
    1.18
    K
    1.14
    M
    1.13
    aren
    1.10
    R
    1.10
     \
    1.09
    POSITIVE LOGITS
    3
    1.30
    τές
    1.09
     especiales
    1.03
    ни
    0.98
    ти
    0.98
     ordinaire
    0.94
     porches
    0.94
    া
    0.93
    ين
    0.93
     idee
    0.93
    Activations Density 0.001%

    No Known Activations