© 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. 17452
    Prev
    Next
    INDEX
    Explanations

    reporting statements and facts

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

    Ljubljana, Russia, experiment

    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
     ভয়ঙ্কর
    0.45
     Recognizing
    0.43
     Utilizing
    0.42
     Undoubtedly
    0.41
    țin
    0.40
     utiliz
    0.40
     localized
    0.40
     ș
    0.39
     આનંદ
    0.39
     이곳
    0.39
    POSITIVE LOGITS
     moreover
    0.55
    Moreover
    0.44
     եւ
    0.44
     причем
    0.43
     пенсии
    0.43
    無い
    0.43
     muß
    0.43
    STA
    0.43
     asses
    0.42
     STA
    0.42
    Activations Density 0.004%

    No Known Activations