© 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-16K
    7. 3660
    Prev
    Next
    INDEX
    Explanations

    leaving a restrictive state

    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
    belum
    0.43
     Aucun
    0.40
    猕
    0.39
    全世界
    0.39
    Questo
    0.39
    ไม่มี
    0.38
    落下
    0.38
     unprocessed
    0.38
    bersihan
    0.37
    在此
    0.37
    POSITIVE LOGITS
     khỏi
    0.78
     confines
    0.54
     from
    0.51
     clutches
    0.46
     into
    0.43
     escapar
    0.43
     շ
    0.43
     quitter
    0.43
     prisons
    0.42
     cramped
    0.42
    Activations Density 0.166%

    No Known Activations