© 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. 12521
    Prev
    Next
    INDEX
    Explanations

    defining key concepts

    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
     Imágenes
    0.59
     सकता
    0.54
     कैलकु
    0.54
     능
    0.54
     能力
    0.53
    襁
    0.53
     بل
    0.52
    ㏄
    0.52
     อย่าง
    0.52
     해결
    0.52
    POSITIVE LOGITS
    ish
    0.49
    '
    0.48
    :
    0.46
     emphasis
    0.45
     important
    0.45
    a
    0.45
     documents
    0.44
     maintenance
    0.44
     rebels
    0.43
     application
    0.43
    Activations Density 0.006%

    No Known Activations