© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2022
    Prev
    Next
    INDEX
    Explanations

    numbered list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    0.30
    0.29
    -
    0.26
    ,
    0.25
    <0xE3>
    0.24
    1
    0.23
    <eos>
    0.23
       
    0.23
    (
    0.23
     M
    0.22
    POSITIVE LOGITS
     kttt
    0.30
     prachtige
    0.29
     protéines
    0.29
    <unused195>
    0.28
     bactéries
    0.28
     txtbtn
    0.28
     namik
    0.28
    <unused2132>
    0.28
     ventanas
    0.27
    <unused1030>
    0.27
    Activations Density 0.689%

    No Known Activations