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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11597
    Prev
    Next
    INDEX
    Explanations

    urls or web addresses

    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
    싯
    0.42
    ेंट
    0.41
    But
    0.40
    MyToolkit
    0.39
      
    0.39
    Footer
    0.38
    antam
    0.38
    Placeholder
    0.37
    頒
    0.37
    About
    0.37
    POSITIVE LOGITS
     tych
    0.44
     índ
    0.41
     tohoto
    0.41
     pohyb
    0.40
     vídeo
    0.39
     myös
    0.39
     podľa
    0.39
     nieuws
    0.39
     indist
    0.38
     indisc
    0.38
    Activations Density 0.002%

    No Known Activations