© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7407
    Prev
    Next
    INDEX
    Explanations

    illegal activities or crimes

    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
     gracefully
    0.63
     മികച്ച
    0.59
    品质
    0.59
     বিশ্বের
    0.57
     automatisch
    0.54
    优化
    0.53
     graceful
    0.53
    它
    0.52
     வழங்கும்
    0.52
     unsere
    0.51
    POSITIVE LOGITS
     unlawfully
    0.86
     unlawful
    0.85
     illegally
    0.81
     ilegal
    0.79
     harassing
    0.77
     defendant
    0.76
     allegedly
    0.75
     Defendant
    0.75
     alleged
    0.74
     कथित
    0.71
    Activations Density 0.147%

    No Known Activations