© 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. 31-GEMMASCOPE-2-RES-262K
    7. 108399
    Prev
    Next
    INDEX
    Explanations

    legal liability and outcomes

    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_31_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
    Signs
    0.48
    Geschichte
    0.47
    থিত
    0.47
    Math
    0.46
    Astronom
    0.46
    柰
    0.46
    ī
    0.46
    arlı
    0.45
    ᴊ
    0.43
    Science
    0.42
    POSITIVE LOGITS
     mandate
    0.57
     category
    0.51
     obligation
    0.51
     contractual
    0.50
     privilege
    0.50
     lobbying
    0.50
     postings
    0.50
     payments
    0.49
     decision
    0.49
     povinn
    0.48
    Activations Density 0.003%

    No Known Activations