© 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-16K
    7. 11501
    Prev
    Next
    INDEX
    Explanations

    running hand through hair

    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_16k_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
    ᓕ
    0.41
     enforce
    0.41
    Frog
    0.40
     titrated
    0.40
     scallop
    0.39
    ੭
    0.39
     fish
    0.38
     calibrate
    0.37
    Appendix
    0.37
     scallops
    0.37
    POSITIVE LOGITS
     уже
    0.46
     Already
    0.43
     Resources
    0.42
     পরিবর্ত
    0.41
    堺
    0.41
     already
    0.40
    已经是
    0.40
    NET
    0.39
    already
    0.39
     !,
    0.38
    Activations Density 0.023%

    No Known Activations