© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3241
    Prev
    Next
    INDEX
    Explanations

    crime and dishonesty

    np_acts-logits-general · gemini-2.5-flash-lite

    criminal activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spinors
    0.43
    টিয়ে
    0.43
    ReLU
    0.42
     آزمایش
    0.41
     monotonic
    0.41
     செயற்க
    0.40
    닿
    0.40
     setImage
    0.40
     neuroscience
    0.39
    ಭಾವ
    0.39
    POSITIVE LOGITS
     theft
    3.84
     thefts
    3.75
     thieves
    3.61
    盗
    3.48
     thief
    3.41
     Theft
    3.41
     stealing
    3.36
     stolen
    3.23
     steal
    3.14
     चोरी
    3.14
    Activations Density 0.273%

    No Known Activations