© 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-65K
    7. 63999
    Prev
    Next
    INDEX
    Explanations

    stealth and secrecy

    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_65k_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
     ঝাঁ
    0.54
    ঋ
    0.46
     substantive
    0.40
    刳
    0.39
     qualcosa
    0.39
     philosophers
    0.39
     unprofitable
    0.38
     inundated
    0.38
    疆
    0.38
     philosophical
    0.38
    POSITIVE LOGITS
     stealth
    1.45
     Stealth
    1.16
     sneaking
    1.14
     sneak
    1.13
     sneaky
    1.06
     Sne
    1.01
     secretly
    0.98
     clandestine
    0.98
     clandest
    0.97
    偷偷
    0.95
    Activations Density 0.141%

    No Known Activations