© 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. 16-GEMMASCOPE-2-RES-262K
    7. 8500
    Prev
    Next
    INDEX
    Explanations

    government security and justice departments

    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_16_width_262k_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
    ות
    0.59
    ه
    0.59
     আসা
    0.57
    仩
    0.56
    л
    0.55
    ഽ
    0.54
     as
    0.54
    
    0.54
     hasn
    0.54
    ：《
    0.53
    POSITIVE LOGITS
     МВД
    0.79
    Police
    0.70
     పోలీ
    0.68
     پولیس
    0.67
    police
    0.63
     полицей
    0.61
     ಪೊಲೀ
    0.59
     ಪೊಲೀಸ
    0.59
    crime
    0.58
     policeman
    0.58
    Activations Density 0.008%

    No Known Activations