© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14648
    Prev
    Next
    INDEX
    Explanations

    should be

    np_acts-logits-general · gemini-2.5-flash-lite

    should

    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_31_width_16k_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
    স
    0.72
     لهم
    0.61
    profiss
    0.58
    সম্প
    0.57
    িস
    0.56
     לק
    0.55
    达成
    0.54
    內
    0.53
     對
    0.52
     הם
    0.52
    POSITIVE LOGITS
     should
    0.97
     SHOULD
    0.94
     Should
    0.86
    Should
    0.83
     powinno
    0.83
     powin
    0.81
     devraient
    0.80
     dovrebbe
    0.80
     shouldn
    0.79
     ideally
    0.77
    Activations Density 0.280%

    No Known Activations