© 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. 40-GEMMASCOPE-2-RES-262K
    7. 99708
    Prev
    Next
    INDEX
    Explanations

    arrest and custody

    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_40_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
     investigation
    0.45
     investigação
    0.44
     investigar
    0.40
     investigating
    0.39
    盜
    0.39
    Investigations
    0.39
    プリ
    0.38
    消耗
    0.38
    ಖ
    0.38
     ث
    0.38
    POSITIVE LOGITS
     custody
    0.88
     Cust
    0.69
    Cust
    0.66
     custard
    0.63
    cust
    0.61
     custod
    0.57
    Custodian
    0.57
     custodia
    0.55
     custodial
    0.54
     हिरासत
    0.54
    Activations Density 0.007%

    No Known Activations