© 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. 14311
    Prev
    Next
    INDEX
    Explanations

    stealing and 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_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
     Ramb
    0.49
    on
    0.49
    an
    0.47
    伤
    0.46
    ガラ
    0.43
    ar
    0.42
     गड्
    0.42
     encephal
    0.41
     promulg
    0.41
     Purch
    0.40
    POSITIVE LOGITS
     steals
    1.23
     steal
    1.19
     stealing
    1.14
    盗
    1.05
     theft
    1.02
    盜
    1.00
     thefts
    1.00
     stole
    0.99
    steal
    0.98
     stolen
    0.93
    Activations Density 0.103%

    No Known Activations