© 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. 84693
    Prev
    Next
    INDEX
    Explanations

    jurisdictions

    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
     embarrassed
    0.43
     embarrassment
    0.40
     হতা
    0.40
     demek
    0.38
    ጋ
    0.38
     rasa
    0.38
     compressibility
    0.38
     ennen
    0.38
     създа
    0.38
     przesz
    0.38
    POSITIVE LOGITS
     jurisdictions
    0.54
     jurisdiction
    0.50
     Jurisdiction
    0.44
    州
    0.42
    juris
    0.42
     LLC
    0.41
     jurisdict
    0.41
     ચા
    0.40
    限制
    0.39
     jurisdic
    0.39
    Activations Density 0.000%

    No Known Activations