© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1946
    Prev
    Next
    INDEX
    Explanations

    arrest and detention related actions

    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
     বিপর্যয়
    0.51
    災害
    0.46
     മികച്ച
    0.46
     বিপর্য
    0.45
     تأثير
    0.44
    灾
    0.44
     നേടിയ
    0.44
     Donation
    0.43
    绚
    0.43
     nutzen
    0.43
    POSITIVE LOGITS
     detained
    2.27
     imprisonment
    2.25
     arrested
    2.23
     arrest
    2.22
     imprisoned
    2.14
     jailed
    2.13
     detention
    2.09
     detain
    2.09
    arrest
    2.09
     incarceration
    2.05
    Activations Density 0.242%

    No Known Activations