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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 99819
    Prev
    Next
    INDEX
    Explanations

    police and criminal activity

    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_all/layer_41_width_262k_l0_big
    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
     nitrous
    0.36
     ত্রিপ
    0.34
     questioning
    0.34
     qualifier
    0.34
     qualifying
    0.34
     ansvar
    0.33
     Heft
    0.33
     छ
    0.33
    సూ
    0.33
    ner
    0.33
    POSITIVE LOGITS
     DBS
    0.90
    Criminal
    0.88
     Criminal
    0.84
     criminal
    0.77
     CRIMINAL
    0.71
    criminal
    0.70
     kriminal
    0.68
    Police
    0.66
    police
    0.62
     경찰
    0.61
    Activations Density 0.000%

    No Known Activations