© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4607
    Prev
    Next
    INDEX
    Explanations

    code syntax and operators

    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
    ；
    0.39
     there
    0.36
    报错
    0.35
    赳
    0.35
    ，
    0.35
     했다
    0.34
     барои
    0.34
     ။
    0.34
     There
    0.33
     없고
    0.33
    POSITIVE LOGITS
    RELATES
    0.37
     chiens
    0.35
     tardes
    0.35
     ކ
    0.32
     disert
    0.32
     alliances
    0.32
     leves
    0.32
    erler
    0.32
    )+'
    0.31
     S
    0.31
    Activations Density 0.160%

    No Known Activations