© 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. 31-GEMMASCOPE-2-RES-65K
    7. 13178
    Prev
    Next
    INDEX
    Explanations

    even small amounts are useful

    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_65k_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
     دقی
    0.38
     คลิ
    0.37
    咛
    0.36
    ண்டு
    0.35
     quietly
    0.35
     طبیعی
    0.35
     echoed
    0.35
    柔
    0.35
     oub
    0.34
    ட்ரோ
    0.34
    POSITIVE LOGITS
     zumindest
    0.91
     atleast
    0.79
     almeno
    0.78
    至少
    0.73
    だけでも
    0.73
    少なくとも
    0.70
     অন্তত
    0.66
    とりあえず
    0.60
     حداقل
    0.60
     किमान
    0.55
    Activations Density 0.196%

    No Known Activations