© 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-262K
    7. 83706
    Prev
    Next
    INDEX
    Explanations

    critical, crucial, explore, consequences

    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_262k_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
    ParentElement
    0.48
    朱
    0.46
    CurrentByte
    0.45
    льбе
    0.44
     durchgeführt
    0.44
    Snippet
    0.44
    GreaterThan
    0.43
     $_
    0.43
    бина
    0.43
     подписа
    0.43
    POSITIVE LOGITS
     are
    0.51
     wages
    0.48
     accommodations
    0.47
    이어
    0.46
     병
    0.46
     accommodates
    0.45
     عین
    0.45
    鉚
    0.44
     accommodating
    0.44
     mismanagement
    0.44
    Activations Density 0.004%

    No Known Activations