© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 19359
    Prev
    Next
    INDEX
    Explanations

    settling or leaning back

    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_16_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
    י
    0.70
    Bench
    0.65
     Would
    0.64
     Bottles
    0.64
     dienst
    0.63
    Would
    0.62
    Ｋ
    0.62
     Haven
    0.61
    Field
    0.61
    ที่
    0.61
    POSITIVE LOGITS
    。
    0.72
     времени
    0.56
    ાર
    0.55
    போது
    0.55
    оне
    0.54
    કાર
    0.54
     ہوں۔
    0.54
     opérateur
    0.53
    时间的
    0.52
     generalised
    0.51
    Activations Density 0.003%

    No Known Activations