© 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. 17543
    Prev
    Next
    INDEX
    Explanations

    ranging from

    np_acts-logits-general · gemini-2.5-flash-lite

    context and company overview

    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
    難
    0.43
    难
    0.40
     interess
    0.39
    واقع
    0.39
    সম
    0.38
     интересно
    0.38
    DELAY
    0.38
     quelcon
    0.38
    晩
    0.37
     реали
    0.37
    POSITIVE LOGITS
     uph
    0.44
    と呼ば
    0.39
    ख्ती
    0.38
     submersible
    0.38
     توضیح
    0.38
    esley
    0.38
     contagious
    0.38
     sawdust
    0.37
     inoc
    0.37
    issau
    0.36
    Activations Density 0.000%

    No Known Activations