© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 64622
    Prev
    Next
    INDEX
    Explanations

    you would

    np_acts-logits-general · gemini-2.5-flash-lite

    right, obligation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rocky
    0.45
     beds
    0.42
     tầm
    0.42
    ঙ্গার
    0.41
     brack
    0.41
    卷
    0.40
     course
    0.40
     cascade
    0.39
     stack
    0.39
     basic
    0.39
    POSITIVE LOGITS
    Liste
    0.52
    𝗨
    0.50
    ibrant
    0.48
     Jh
    0.48
    ベージュ
    0.48
     entreprises
    0.47
     yil
    0.47
     حمایت
    0.46
    epar
    0.46
     मंजूर
    0.46
    Activations Density 0.000%

    No Known Activations