© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1454
    Prev
    Next
    INDEX
    Explanations

    evaluating or rating criteria

    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_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
    ر
    0.52
    ت
    0.45
    ن
    0.44
      
    0.42
    J
    0.42
    8
    0.41
     modificaciones
    0.40
    к
    0.40
    ب
    0.40
    octet
    0.40
    POSITIVE LOGITS
     गिवन
    0.50
     กลุ่ม
    0.46
     slams
    0.46
     pulsing
    0.45
     theorists
    0.44
    cohol
    0.44
     encourages
    0.44
     steels
    0.43
     आएंगी
    0.43
     Bulg
    0.43
    Activations Density 0.002%

    No Known Activations