© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1957
    Prev
    Next
    INDEX
    Explanations

    unit scope

    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
     দেখিলাম
    0.24
     ค่ะ
    0.23
     হইয়া
    0.22
     গিয়া
    0.21
     কারন
    0.20
    ()=>{
    0.19
     ব্যপারে
    0.19
     করিয়া
    0.19
     đc
    0.19
    ɪ
    0.19
    POSITIVE LOGITS
     elsewhere
    0.33
     domestically
    0.27
     regardless
    0.27
     despite
    0.26
     solely
    0.26
     beforehand
    0.26
     regionally
    0.26
     altogether
    0.25
     anyways
    0.24
     anyway
    0.24
    Activations Density 3.947%

    No Known Activations