© 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. 10716
    Prev
    Next
    INDEX
    Explanations

    don't intervene physically

    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
     tradition
    0.41
     sag
    0.40
    涹
    0.40
    ūsų
    0.40
    ម្បី
    0.39
     nü
    0.39
    անկ
    0.39
    ljenje
    0.39
     सकारात्मक
    0.39
     belieb
    0.39
    POSITIVE LOGITS
     incapac
    0.45
     εκεί
    0.42
    깝
    0.40
    מר
    0.39
    ather
    0.39
     pouvant
    0.39
     collapsible
    0.39
     disabled
    0.39
    の発
    0.38
     sorpresa
    0.38
    Activations Density 0.075%

    No Known Activations