© 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-16K
    7. 8080
    Prev
    Next
    INDEX
    Explanations

    main method or script entry

    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
     Proble
    0.50
     Nú
    0.46
     Konfl
    0.45
     Arten
    0.44
    ޏ
    0.43
     Quis
    0.43
    instances
    0.43
     Funktionen
    0.42
    Proble
    0.42
    岀
    0.42
    POSITIVE LOGITS
    евского
    0.48
     ribs
    0.43
     retracted
    0.42
    ("{
    0.41
     ніж
    0.41
    เวณ
    0.40
    шему
    0.40
    iceras
    0.40
    яви
    0.40
    ంలో
    0.39
    Activations Density 0.074%

    No Known Activations