© 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. 9509
    Prev
    Next
    INDEX
    Explanations

    sensitive data theft

    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
     calibration
    0.48
     refus
    0.48
     refusal
    0.47
     inhibits
    0.44
     phenotypic
    0.44
    拒
    0.44
     preservatives
    0.43
     refuses
    0.42
     mecanismos
    0.42
     mechanistic
    0.42
    POSITIVE LOGITS
    窃
    0.58
    盗
    0.57
    竊
    0.52
     steals
    0.46
    盜
    0.46
     thief
    0.46
     stolen
    0.46
     Theft
    0.45
     অমিত
    0.45
    데이터
    0.45
    Activations Density 0.344%

    No Known Activations