© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    study, quiz, textbook, tutor

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

    automated AI tasks

    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
     abrog
    0.48
    дравствуйте
    0.39
     பெயர்
    0.38
    年月日
    0.38
    جنة
    0.38
    امله
    0.37
    čnost
    0.37
    様
    0.37
    avení
    0.36
     Etat
    0.36
    POSITIVE LOGITS
     Ace
    0.79
     Textbook
    0.73
     ACE
    0.69
     Video
    0.68
     ace
    0.68
    Ace
    0.68
     textbooks
    0.67
     tutor
    0.67
     textbook
    0.66
     Quiz
    0.66
    Activations Density 0.003%

    No Known Activations